Practical AI workflows

Run Bonsai 2 · 27B locally for private chat using PrismML's llama.cpp fork. Choose an official ternary package or a community CRACK uncensored build, then follow the route for your operating system and accelerator backend.

Freshness 82 out of 100. Release age: 52 days old, Sep 17, 2026. Measures age, not quality.

SOFTWAREGit + PrismML Bonsai Demo + PrismML llama.cpp fork

LOCALRENTED GPU

Estimated

Coding

SETUP GUIDE

Build a local coding assistant with Bonsai 2 · 27B

Stand up a private, on-device coding assistant: pick a Bonsai 2 · 27B ternary GGUF package, serve it with the PrismML llama.cpp fork, connect the local OpenAI-compatible endpoint to Cline in VS Code, and complete one small, reviewable code change. Bonsai 2 · 27B is a 27.36B-parameter hybrid-attention model with a 262K-token context, so a single workstation can hold a full assistant-sized model; the packed PQ2_0 and PTQ1_0 types only run correctly in the PrismML fork, not stock llama.cpp or Ollama.

Freshness 82 out of 100. Release age: 52 days old, Sep 17, 2026. Measures age, not quality.

SOFTWAREPrismML llama.cpp fork (Bonsai demo) + VS Code + Cline

Build a local tool-using agent with Bonsai 2 · 27B

Source-backed metadata for a local agent setup using Bonsai 2 · 27B with PrismML’s llama.cpp fork and Hermes Agent. Choose the smallest official PTQ1_0 pack, a community abliterated PTQ1_0 alternative, or the official PQ2_0 pack used in PrismML’s agent demo.

Freshness 82 out of 100. Release age: 52 days old, Sep 17, 2026. Measures age, not quality.

SOFTWAREPrismML llama.cpp fork + Hermes Agent

Run a private reasoning assistant with Bonsai 2 · 27B

Select a source-backed Bonsai 2 · 27B package, start the PrismML llama.cpp fork, then verify a multi-step reasoning answer locally.

Freshness 82 out of 100. Release age: 52 days old, Sep 17, 2026. Measures age, not quality.

SOFTWAREGit + PrismML Bonsai Demo + PrismML llama.cpp fork

Generate MiniMax H3 video with audio in ComfyUI

Generate a short local MiniMax H3 video with synchronized sound in ComfyUI using the supported NVIDIA or Apple Silicon package for your machine.

Freshness 69 out of 100. Release age: 97 days old, Aug 3, 2026. Measures age, not quality.

Generate MiniMax H3 videos with FreeVideo

Install FreeVideo’s managed ComfyUI workspace on Windows, Linux, an experimental Apple Silicon Mac, or a rented RunPod GPU. Generate and save a MiniMax H3 video with audio, then try image-to-video, previews, and optional automation.

Freshness 69 out of 100. Release age: 97 days old, Aug 3, 2026. Measures age, not quality.

SOFTWAREFreeVideo Desktop + FreeVideo + ComfyUI

Review security with DeepSeek V4.1 Flash and Hermes

Connect Hermes to an uncensored DeepSeek V4.1 Flash API, review your own code, and save a report with evidence and suggested fixes. Choose Venice or Experiential Labs; no GPU rental is required.

Freshness 80 out of 100. Repository age: 59 days old, Sep 10, 2026. Measures age, not quality.

SOFTWAREHermes Agent + OpenAI-compatible API

Run DeepSeek V4.1 Flash Uncensored with Strata

Run AtomicChat’s IQ2_XXS backbone with ISTA’s separate Engram table through Strata on Windows, Apple Silicon Mac, Linux or RunPod. Includes separate copyable commands, hardware guidance, browser verification and local/cloud API connections for tools.

Freshness 80 out of 100. Repository age: 59 days old, Sep 10, 2026. Measures age, not quality.

SOFTWAREStrata + Hugging Face CLI

Create images locally with Qwen-Image-2.1

Create an image with the official Qwen Image 2.1 ComfyUI template, or choose the publisher Turbo pipeline for a faster eight-step route.

Freshness 81 out of 100. Repository age: 55 days old, Sep 14, 2026. Measures age, not quality.

Arena Open Source Image generation: rank 1 of 19. Ranked model: Qwen-Image-2.1. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.+1

SOFTWAREComfyUI + Diffusers

Edit images locally with Qwen-Image-2.1

Edit your own image using the official Qwen Image 2.1 ComfyUI template, or choose the publisher Turbo pipeline. Select a package and follow its exact files and settings.

Freshness 81 out of 100. Repository age: 55 days old, Sep 14, 2026. Measures age, not quality.

Arena Open Source Image generation: rank 1 of 19. Ranked model: Qwen-Image-2.1. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.+1

SOFTWAREComfyUI + Diffusers

Build a private AI agent with GLM-5.3 Flash

Serve GLM-5.3 Flash · FP8 privately, connect Hermes to the model endpoint, and have the agent inspect files and produce a review checklist.

Freshness 75 out of 100. Repository age: 75 days old, Aug 25, 2026. Measures age, not quality.

Arena Open Source Agents: rank 10 of 23. Ranked model: GLM-5.3-Flash. Original model ranking, not a benchmark of this package. Export dated Nov 4, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.+3

SOFTWAREvLLM CUDA Docker + Hermes Agent

Code with GLM-5.3 Flash in VS Code + Cline

Serve GLM-5.3 Flash · FP8 privately, connect VS Code and Cline, then review and test a real code change.

Freshness 75 out of 100. Repository age: 75 days old, Aug 25, 2026. Measures age, not quality.

Arena Open Source Agents: rank 10 of 23. Ranked model: GLM-5.3-Flash. Original model ranking, not a benchmark of this package. Export dated Nov 4, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.+3

SOFTWAREvLLM CUDA Docker + VS Code + Cline

Run GLM-5.3 with Strix for Authorized Security Reviews

Choose GLM-5.3 Flash or full GLM-5.3, then run Strix with a self-hosted Linux cluster, rented RunPod GPUs, or the OpenRouter hosted API to review a disposable repository you are authorized to assess.

Freshness 75 out of 100. Repository age: 75 days old, Aug 25, 2026. Measures age, not quality.

Arena Open Source Agents: rank 4 of 23. Ranked model: GLM-5.3 (Max). Original model ranking, not a benchmark of this package. Export dated Nov 4, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.+2

SOFTWAREvLLM + Strix + Docker + RunPod + OpenRouter

Build a private AI agent with Qwen3.8-Flash-Next

Run the official high-memory package, connect Hermes to its private Ollama endpoint, and produce a checked project review.

Freshness 75 out of 100. Repository age: 76 days old, Aug 24, 2026. Measures age, not quality.

SOFTWAREOllama + Hermes Agent

Code with Qwen3.8-Flash-Next in VS Code + Cline

Use the base Qwen3.8-Flash-Next checkpoint with VS Code and Cline, review a real code change, and test it. This is separate from the Strata derivative.

Freshness 75 out of 100. Repository age: 76 days old, Aug 24, 2026. Measures age, not quality.

SOFTWAREOllama + VS Code + Cline

Set up private chat with Qwen3.8-27B

Run a private local chat using Ollama with Qwen3.8-27B, send a first prompt, and confirm the model responds.

Freshness 69 out of 100. Repository age: 95 days old, Aug 5, 2026. Measures age, not quality.

Arena Open Source Web coding: rank 12 of 62. Ranked model: Qwen3.8-27B. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.+3

Build a local AI agent with Qwen3.8 27B

Run Qwen3.8 with Ollama, connect Hermes Agent, and produce a source-checked local project review on your machine or a private rental.

Freshness 69 out of 100. Repository age: 95 days old, Aug 5, 2026. Measures age, not quality.

SOFTWAREOllama + Hermes Agent

Build a private coding assistant with Qwen3.8 27B

Run Qwen3.8 27B with Ollama, connect it to Cline in VS Code, and make one reviewable code change in a tiny local project.

Freshness 69 out of 100. Repository age: 95 days old, Aug 5, 2026. Measures age, not quality.

Arena Open Source Web coding: rank 12 of 62. Ranked model: Qwen3.8-27B. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.+3

SOFTWAREOllama + Visual Studio Code + Cline + Python

Animate a character with Wan Animate 2

Transfer motion from a driving video onto a character image using the official Wan Animate 2 ComfyUI workflow and its complete five-file model set.

Freshness 70 out of 100. Release age: 93 days old, Aug 7, 2026. Measures age, not quality.

Set up private chat with Gemma 4 · 12B

Run a private local chat with Gemma 4 · 12B using Ollama on Windows, macOS, or Linux. You will install the runtime, fetch the 7.6 GB text-and-image model package, start a chat session, send a first prompt, and confirm the model responds.

Freshness 52 out of 100. Repository age: 169 days old, May 23, 2026. Measures age, not quality.

Ask questions about an image privately with Gemma 4

Use Gemma 4 12B through Ollama to answer questions about a local image without uploading it to a hosted model. Check its answer against the visible photo.

Freshness 52 out of 100. Repository age: 169 days old, May 23, 2026. Measures age, not quality.

Set up private Gemma 4 chat

Choose official QAT packages for Gemma 4 E2B, E4B, or 12B, or a clearly marked community abliterated E4B package; follow Mac, Windows, or Linux instructions for your choice.

Freshness 43 out of 100. Release age: 220 days old, Apr 2, 2026. Measures age, not quality.

Chat locally with Qwen3.5 · 4B

Chat privately with Qwen3.5 4B in the Ollama app on Windows or Mac, or in its interactive Terminal on Linux. Start the exact 3.4 GB package at 4K context and check a follow-up message.

Freshness 38 out of 100. Repository age: 254 days old, Feb 27, 2026. Measures age, not quality.

Analyze images locally with Qwen3.5

Set up Qwen3.5 for local image understanding through a receipt-extraction example. Choose the lighter 2B or more capable 4B package, upload a receipt, and compare the extracted fields with the original. The supplied app is a dedicated receipt reader, not a general image-chat interface.

Freshness 38 out of 100. Repository age: 254 days old, Feb 27, 2026. Measures age, not quality.

SOFTWAREOllama + Gradio

Create Uncensored AI Bots with Rakazo

Create persistent Rakazo bots with Huihui’s uncensored Qwen3 8B. Choose local Ollama or the documented 48 GB RunPod Serverless Load Balancer vLLM setup.

Freshness 12 out of 100. Repository age: 560 days old, Apr 27, 2025. Measures age, not quality.

SOFTWARERakazo + Docker + Ollama / vLLM

Build a local AI agent team with Qwen3 8B

Build a local AI agent team with Qwen3 8B, Ollama and CrewAI. The example assigns reader, writer and reviewer roles to compare two product briefs, with source reads, task handoffs and a final Markdown file you can inspect.

Freshness 12 out of 100. Repository age: 560 days old, Apr 27, 2025. Measures age, not quality.

SOFTWAREOllama + CrewAI + uv + Python 3.12

Build a local AI tool agent with Qwen3 8B

Run a bounded local function through Qwen3 8B and inspect the tool call, tool result, and final answer.

Freshness 12 out of 100. Repository age: 560 days old, Apr 27, 2025. Measures age, not quality.

SOFTWAREOllama + Python

Set up private chat with DeepSeek R1 · 14B

Install Ollama, pull the DeepSeek R1 14B distilled model, start a local chat, and verify the model responds to a first prompt using only the documented Ollama command.

Freshness 8 out of 100. Repository age: 657 days old, Jan 20, 2025. Measures age, not quality.

SOFTWAREOllama + DeepSeek R1 · 14B (deepseek-r1:14b)

Run a private reasoning assistant with DeepSeek R1 · 14B

Run DeepSeek R1 14B privately with Ollama. Start the documented package, try a known reasoning problem, and check the answer before using it for harder work.

Freshness 8 out of 100. Repository age: 657 days old, Jan 20, 2025. Measures age, not quality.

SOFTWAREOllama + DeepSeek R1 14B (deepseek-r1:14b model)

Set up private chat with Qwen2.5 Coder · 7B

Install Ollama and run the Qwen2.5-Coder-7B-Instruct model locally with `ollama run qwen2.5-coder:7b`, then send a first coding prompt and confirm the model responds with generated code.

Freshness 5 out of 100. Repository age: 782 days old, Sep 17, 2024. Measures age, not quality.

SOFTWAREOllama + Qwen/Qwen2.5-Coder-7B-Instruct

Generate videos locally with Wan2.1

Turn text prompts into local videos with the Wan2.1 T2V 1.3B model, complete pipeline files and a ready-to-load ComfyUI workflow.

Freshness 9 out of 100. Repository age: 621 days old, Feb 25, 2025. Measures age, not quality.

Set up private chat with Gemma 3 · 4B

Run a private local chat with Gemma 3 4B using Ollama on Windows, macOS, or Linux. Start the runtime, load the gemma3:4b model, send a first text prompt, and confirm the model responds from your machine.

Freshness 9 out of 100. Repository age: 626 days old, Feb 20, 2025. Measures age, not quality.

Arena Open Source Text: rank 119 of 228. Ranked model: Gemma 3 4B IT. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.

SOFTWAREOllama + Gemma 3 4B (gemma3:4b)

Ask your documents locally with Qwen3.5 · 9B

Ask Qwen3.5 9B about a short local document and check the answer against source text. Attach a text file or text-based PDF in the Ollama app on Windows or Mac, or paste a short text excerpt into its Linux chat.

Freshness 38 out of 100. Release age: 254 days old, Feb 27, 2026. Measures age, not quality.

Create images locally with FLUX.2 Klein

Generate images from text prompts in ComfyUI with the fast distilled or more adjustable base 4B model. Save your results and reuse the visual workflow.

Freshness 32 out of 100. Release age: 297 days old, Jan 15, 2026. Measures age, not quality.

Edit images locally with FLUX.2 Klein

Upload an image, describe the changes you want and save the edited result in ComfyUI. This reference-guided workflow supports a range of visual edits; it does not use an inpainting mask.

Freshness 32 out of 100. Release age: 297 days old, Jan 15, 2026. Measures age, not quality.

Build a private coding assistant on rented GPUs

Rent two NVIDIA GPUs to serve Mistral Small 4 privately through vLLM, connect Cline in your local VS Code, and create and test a small local Python file.

Freshness 33 out of 100. Repository age: 289 days old, Jan 23, 2026. Measures age, not quality.

SOFTWAREvLLM + VS Code + Cline + Runpod

Set up private chat with gpt-oss · 20B

Install Ollama, pull the gpt-oss:20b model, launch a local private chat session, send a first prompt, and verify the model responds.

Freshness 17 out of 100. Repository age: 461 days old, Aug 4, 2025. Measures age, not quality.

Arena Open Source Text: rank 110 of 228. Ranked model: gpt-oss-20b. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.

SOFTWAREOllama + gpt-oss:20b

Extract structured data locally with gpt-oss 20B

Extract and validate a sample receipt with gpt-oss 20B through local Ollama and Python.

Freshness 17 out of 100. Repository age: 461 days old, Aug 4, 2025. Measures age, not quality.

Arena Open Source Text: rank 110 of 228. Ranked model: gpt-oss-20b. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.

SOFTWAREOllama + Python + Pydantic

Run a private reasoning assistant with gpt-oss · 20B

Install Ollama, pull and run gpt-oss:20b locally, set a reasoning level, and verify a reasoning response from the model. This uses the publisher-documented Ollama path for the gpt-oss-20b open-weight model, which requires the Harmony response format and supports configurable low, medium, and high reasoning effort.

Freshness 17 out of 100. Repository age: 461 days old, Aug 4, 2025. Measures age, not quality.

Arena Open Source Text: rank 110 of 228. Ranked model: gpt-oss-20b. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.

SOFTWAREOllama + gpt-oss:20b

Chat locally with Qwen3-Coder-Next

Chat privately with Qwen3-Coder-Next in the Ollama app on Windows or Mac, or its interactive Terminal on Linux. Choose official Q4, higher-precision Q8, or an uncensored package, then start a conversation with a practical 4K context.

Freshness 34 out of 100. Repository age: 282 days old, Jan 30, 2026. Measures age, not quality.

Build a local AI agent with Qwen3-Coder-Next

Connect Qwen3-Coder-Next to Cline for a local AI agent that can work with files in your workspace. The example compares two product briefs, shows its file tools in action, and saves a cited result for you to inspect.

Freshness 34 out of 100. Repository age: 282 days old, Jan 30, 2026. Measures age, not quality.

SOFTWAREOllama + Visual Studio Code + Cline

Build a local coding assistant with Qwen3-Coder-Next

Connect Qwen3-Coder-Next to Cline in VS Code for a private local coding assistant. The example changes a supplied calculator project, then checks the diff and runs independent tests.

Freshness 34 out of 100. Repository age: 282 days old, Jan 30, 2026. Measures age, not quality.

SOFTWAREOllama + Visual Studio Code + Cline + Node.js LTS

Review code privately with Qwen3-Coder-Next on rented GPUs

Rent two NVIDIA GPUs to serve Qwen3-Coder-Next privately through vLLM, connect Cline in your local VS Code, and review a local repository and inspect its suggested fix.

Freshness 34 out of 100. Repository age: 282 days old, Jan 30, 2026. Measures age, not quality.

SOFTWAREvLLM + VS Code + Cline + Runpod

Set up private chat with gpt-oss · 120B

Run the gpt-oss 120B model locally through Ollama, send a first chat prompt, and confirm the model returns a response. This setup is intended for machines with enough memory or GPU capacity to host the 65 GB package; the model is a text-generation model in the gpt-oss series.

Freshness 17 out of 100. Repository age: 461 days old, Aug 4, 2025. Measures age, not quality.

Arena Open Source Text: rank 87 of 228. Ranked model: gpt-oss-120b. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.

SOFTWAREOllama + gpt-oss:120b model

Run a private reasoning assistant with gpt-oss · 120B

Use the official gpt-oss 120B Ollama package for a private reasoning assistant. Choose a starting context that fits your memory, ask a checkable question, and verify the answer.

Freshness 17 out of 100. Repository age: 461 days old, Aug 4, 2025. Measures age, not quality.

Arena Open Source Text: rank 87 of 228. Ranked model: gpt-oss-120b. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.

Transcribe an audio file privately

Use the publisher’s Transformers path for Voxtral Mini Realtime to transcribe a local recording, check the words against the audio, and keep the file off hosted APIs.

Freshness 33 out of 100. Repository age: 291 days old, Jan 21, 2026. Measures age, not quality.

SOFTWAREPython + PyTorch + Transformers + mistral-common

Generate a local video with LTX 2.5 Fast

Install LTX Desktop, load gated LTX 2.5 Fast weights, choose local text encoding, render a short clip, and check the saved video on a supported PC or Mac.

Freshness 66 out of 100. Repository age: 108 days old, Jul 23, 2026. Measures age, not quality.

Run RavenX CyberAgent for Authorized AI Pen Testing

Run the publisher’s RavenX Q4_K_M GGUF locally on Windows, macOS, or Linux, or on a rented RunPod GPU. Serve it with llama.cpp and connect an optional agent to a read-only security-review task.

Freshness 55 out of 100. Repository age: 157 days old, Jun 4, 2026. Measures age, not quality.

SOFTWAREllama.cpp + RunPod + Hermes Agent

Run GLM-5.3 UNCENSORED through an API

Connect a PC client to GLM-5.3 through an API. Hosted options use MagmaRouter’s Xploded or Abliteration.ai’s Large V2 derivatives. The exact dealignai FP8 route uses one eight-H200 RunPod server, persistent storage, a private SSH tunnel, and a supplied API check.

Freshness 76 out of 100. Repository age: 70 days old, Aug 30, 2026. Measures age, not quality.

SOFTWAREvLLM + Python + SSH + RunPod + VS Code + Cline

Build a coding assistant with Strata (Qwen3.8-Flash-Next Coder)

Run Qwen3.8-Flash-Next through Strata, connect VS Code and Cline, and complete a real coding task. Choose the smaller Coder derivative or a full pack, then follow Windows, Linux or RunPod instructions. Compare actual speed, memory use, and tool results on your own setup.

Freshness 75 out of 100. Repository age: 76 days old, Aug 24, 2026. Measures age, not quality.

SOFTWAREStrata + VS Code + Cline

LOCALRENTED GPU

Partially field-tested

Coding

SETUP GUIDE

Code locally with Mellum2.1 Thinking

Serve Mellum2.1 Thinking · 12B BF16 privately, connect VS Code and Cline, then review and test a real code change.

Freshness 83 out of 100. Release age: 49 days old, Sep 20, 2026. Measures age, not quality.

SOFTWAREOllama + VS Code + Cline + vLLM

Build a private AI agent with Kolibri 1

Serve Kolibri 1 · BF16 privately, connect Hermes to the model endpoint, and have the agent inspect files and produce a review checklist.

Freshness 87 out of 100. Release age: 36 days old, Oct 3, 2026. Measures age, not quality.

SOFTWAREAleph Alpha vLLM plugin + Hermes Agent

Create short video with audio using Kandinsky 6 Pro

Generate a five-second video with synchronized audio in the publisher Kandinsky 6 ComfyUI templates. Select the exact full Pro checkpoint, or switch to the easier managed Pro Distill alternative.

Freshness 79 out of 100. Release age: 60 days old, Sep 9, 2026. Measures age, not quality.

SOFTWAREComfyUI + Kandinsky 6 publisher nodes

Create a song locally with YuE2 3B

Create a local song visually with the official ComfyUI YuE2 template and exact 3B int8 checkpoint; publisher Linux wheel and community audio.cpp are available as alternate routes.

Freshness 79 out of 100. Release age: 60 days old, Sep 9, 2026. Measures age, not quality.

SOFTWAREComfyUI + YuE2 inference wheel + audio.cpp WebUI

Create video locally with HunyuanVideo 1.5

Use maintained ComfyUI templates for text-to-video or image-to-video. The task selector changes the exact checkpoint, input, files and steps.

Freshness 26 out of 100. Release age: 353 days old, Nov 20, 2025. Measures age, not quality.

Arena Open Source Text to video: rank 3 of 7. Ranked model: HunyuanVideo 1.5. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.+1

Create a physical-AI scene with Cosmos3 Super

Generate a structured robotics concept image using NVIDIA’s publisher-tested GB200 Diffusers route, then inspect its physical details rather than treating it as simulation data.

Freshness 54 out of 100. Release age: 161 days old, May 31, 2026. Measures age, not quality.

Arena Open Source Image generation: rank 4 of 19. Ranked model: Cosmos3-Super-Text2Image. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.

SOFTWAREDiffusers + Python

Set up private desktop chat with LFM3-1.7B Uncensored

Chat privately with LFM3-1.7B Uncensored in your own browser. Download the exact AtomicChat GGUF, run llama.cpp on Windows, macOS, or Linux, and keep conversations on your computer without a cloud account.

Freshness 95 out of 100. Repository age: 12 days old, Oct 27, 2026. Measures age, not quality.

Set up private phone chat with LFM3-1.7B Uncensored

Set up private local chat with AtomicChat’s compact LFM3 model on your phone. Use OnDevice on iPhone, or follow the documented Android import steps with exact-model compatibility clearly marked as unverified.

Freshness 95 out of 100. Repository age: 12 days old, Oct 27, 2026. Measures age, not quality.

SOFTWAREOnDevice: Local AI Studio + Layla (Android compatibility unverified)

LOCAL

Partially field-tested

Coding

SETUP GUIDE

Build a local coding assistant with MiniCPM5 2B SFT

Import the exact intermediate MiniCPM5 2B SFT weights into Ollama, connect VS Code/Cline, make a small local code change, and inspect the test result.

Freshness 75 out of 100. Repository age: 73 days old, Aug 27, 2026. Measures age, not quality.

SOFTWAREOllama + VS Code + Cline

openbmb/MiniCPM5-2B-GGUF

Publisher GGUF repository with F16, Q8_0, and Q4_K_M files for MiniCPM5 2B. Q4_K_M is about 1.56 GB; F16 is about 5.04 GB.

Freshness 78 out of 100. Repository age: 64 days old, Sep 5, 2026. Measures age, not quality.

Chat privately with uncensored Gemma 4 E4B

Run the publisher’s uncensored Gemma 4 E4B Q4 GGUF with llama.cpp, open the local browser chat, and check a real response.

Freshness 43 out of 100. Repository age: 220 days old, Apr 2, 2026. Measures age, not quality.

Build a coding assistant with GLM 5.2 on rented GPUs

Use a publisher GLM 5.2 checkpoint on a capable multi-GPU Linux host, connect VS Code/Cline privately from Windows or Mac, and verify a small code change.

Freshness 57 out of 100. Repository age: 145 days old, Jun 16, 2026. Measures age, not quality.

SOFTWARESGLang + Runpod + VS Code + Cline

LFM2.5 2.6B local agent setup

Metadata for building a local tool-using agent with LFM2.5 2.6B using Transformers or llama.cpp across Windows, Linux, and macOS.

Freshness 67 out of 100. Repository age: 103 days old, Jul 28, 2026. Measures age, not quality.

SOFTWARETransformers + llama.cpp

Chat privately with Nemotron 3 Nano Omni

Use a source-linked Q4_K_M conversion of NVIDIA Nemotron 3 Nano Omni in Ollama for a reviewable local text chat. The publisher BF16 and full multimodal serving routes remain linked separately.

Freshness 46 out of 100. Repository age: 202 days old, Apr 20, 2026. Measures age, not quality.

Build a local AI agent with Ministral 3 Reasoning

Run an official Ministral 3 Reasoning GGUF on your computer, allow one bounded local lookup, and inspect the tool result and final answer.

Freshness 24 out of 100. Repository age: 373 days old, Oct 31, 2025. Measures age, not quality.

SOFTWAREOllama + Python

Chat locally with MiniCPM5 · 2B

Run the official MiniCPM5 2B GGUF on Windows, Mac, or Linux with Ollama for a simple private chat. An advanced GPTQ/vLLM route is available for Linux NVIDIA, plus a separately labelled community uncensored MLX package for Apple Silicon.

Freshness 79 out of 100. Repository age: 62 days old, Sep 7, 2026. Measures age, not quality.

SOFTWAREOllama + vLLM + mlx-lm

MiniCPM5 2B local coding assistant metadata plan

Metadata-only plan for a local coding assistant using MiniCPM5 2B GPTQ AWQ 4-bit, with portable GGUF and Apple Silicon MLX alternatives. Selects source-backed packages and supported platform routes.

Freshness 79 out of 100. Repository age: 62 days old, Sep 7, 2026. Measures age, not quality.

SOFTWAREllama.cpp + vLLM + MLX

Animate images locally with Wan2.1

Turn still images into silent video clips with the Wan2.1 480p image-to-video model, a ready-to-load ComfyUI workflow and practical memory settings.

Freshness 9 out of 100. Repository age: 621 days old, Feb 25, 2025. Measures age, not quality.

Transcribe audio locally with Whisper large-v3-turbo

Import a recording into Buzz, run Whisper large-v3-turbo locally, review the transcript and export TXT and SRT without building a Python environment.

Freshness 5 out of 100. Repository age: 768 days old, Oct 1, 2024. Measures age, not quality.

SOFTWAREBuzz desktop + OpenAI Whisper large-v3-turbo

Generate speech locally with Kokoro-82M

Write text, generate Kokoro-82M speech, edit and export a WAV in a local visual editor rather than running a custom Python script for every line.

Freshness 7 out of 100. Repository age: 682 days old, Dec 26, 2024. Measures age, not quality.

SOFTWAREKokoroGUI + Kokoro-82M + Python 3.11+ + eSpeak NG

Generate music locally with ACE-Step 1.5

Create music in the official ACE-Step 1.5 local Gradio interface, listen to the result and save its WAV and settings. The first example generates a 30-second instrumental with the publisher turbo model and the optional language model disabled.

Freshness 33 out of 100. Repository age: 289 days old, Jan 23, 2026. Measures age, not quality.

SOFTWAREACE-Step 1.5 official repository + Python 3.11 + uv + Git + FFmpeg + Gradio

Build private search with Qwen3 Embedding

Build a local browser search tool for your text and Markdown documents. Get ranked source passages, keep a reusable index, and export results for the reranking workflow.

Freshness 13 out of 100. Repository age: 523 days old, Jun 3, 2025. Measures age, not quality.

SOFTWARESentence Transformers + Gradio

Improve local search with Qwen3 Reranker

Compare the same search candidates before and after reranking. Use a supplied example or upload the results from your private document search, then export the improved order.

Freshness 13 out of 100. Repository age: 528 days old, May 29, 2025. Measures age, not quality.

SOFTWARESentence Transformers + Gradio

Create images on a rented GPU with SDXL Turbo

Rent one GPU, load the official SDXL Turbo graph in ComfyUI, generate and download an image, then stop or remove the rental. Your own machine only controls the browser.

Freshness 2 out of 100. Repository age: 1,077 days old, Nov 27, 2023. Measures age, not quality.

SOFTWAREComfyUI + Runpod official ComfyUI template + OpenSSH client

Turn your computer into a private AI server with ODS

Install Docker Desktop, run the ODS installer, and open your own local AI interface. Follow the Windows or Apple Silicon Mac setup, verify a model response, and manage your server.

SOFTWAREDocker Desktop + ODS

Run open-source AI apps with Pinokio

Install Pinokio and launch one-click open-source AI apps such as Maestro, either on a rented RunPod GPU in your browser or on your own Windows, Mac or Linux computer.

Control your Android TV with AI using OmarchyTV

Replace the Google TV home screen with OmarchyTV, a terminal-style launcher with 26 themes and a Grok Bot command line, then let an AI agent install it and drive the TV over ADB.

SOFTWAREOmarchyTV + Android Platform-Tools (ADB)

Run a full local AI studio with Imagination Studio

Set up Imagination Studio by keys+Wasserman, a full AI studio for video with sound, images, voice, music, sound effects and editing, from a one-click RunPod template or on a supported high-memory Mac or NVIDIA machine, then make your first clip.

SOFTWAREImagination Studio by keys+Wasserman + TensorFold + ComfyUI (CUDA build)

Set up a local AI server with Open WebUI

Run a persistent, password-protected chat workspace on your own computer. Connect Open WebUI to local Ollama, start with Qwen3.5 4B, and confirm your conversation survives a restart.

SOFTWAREOpen WebUI + Ollama

LOCAL

Estimated

Find a setup for your task.

Your machine

What do you want to run?

Set up private chat with Bonsai 2 · 27B

Build a local coding assistant with Bonsai 2 · 27B

Build a local tool-using agent with Bonsai 2 · 27B

Run a private reasoning assistant with Bonsai 2 · 27B

Generate MiniMax H3 video with audio in ComfyUI

Generate MiniMax H3 videos with FreeVideo

Review security with DeepSeek V4.1 Flash and Hermes

Run DeepSeek V4.1 Flash Uncensored with Strata

Create images locally with Qwen-Image-2.1

Edit images locally with Qwen-Image-2.1

Build a private AI agent with GLM-5.3 Flash

Code with GLM-5.3 Flash in VS Code + Cline

Run GLM-5.3 with Strix for Authorized Security Reviews

Build a private AI agent with Qwen3.8-Flash-Next

Code with Qwen3.8-Flash-Next in VS Code + Cline

Set up private chat with Qwen3.8-27B

Build a local AI agent with Qwen3.8 27B

Build a private coding assistant with Qwen3.8 27B

Animate a character with Wan Animate 2

Set up private chat with Gemma 4 · 12B

Ask questions about an image privately with Gemma 4

Set up private Gemma 4 chat

Chat locally with Qwen3.5 · 4B

Analyze images locally with Qwen3.5

Create Uncensored AI Bots with Rakazo

Build a local AI agent team with Qwen3 8B

Build a local AI tool agent with Qwen3 8B

Set up private chat with DeepSeek R1 · 14B

Run a private reasoning assistant with DeepSeek R1 · 14B

Set up private chat with Qwen2.5 Coder · 7B

Generate videos locally with Wan2.1

Set up private chat with Gemma 3 · 4B

Ask your documents locally with Qwen3.5 · 9B

Create images locally with FLUX.2 Klein

Edit images locally with FLUX.2 Klein

Build a private coding assistant on rented GPUs

Set up private chat with gpt-oss · 20B

Extract structured data locally with gpt-oss 20B

Run a private reasoning assistant with gpt-oss · 20B

Chat locally with Qwen3-Coder-Next

Build a local AI agent with Qwen3-Coder-Next

Build a local coding assistant with Qwen3-Coder-Next

Review code privately with Qwen3-Coder-Next on rented GPUs

Set up private chat with gpt-oss · 120B

Run a private reasoning assistant with gpt-oss · 120B

Transcribe an audio file privately

Generate a local video with LTX 2.5 Fast

Run RavenX CyberAgent for Authorized AI Pen Testing

Run GLM-5.3 UNCENSORED through an API

Build a coding assistant with Strata (Qwen3.8-Flash-Next Coder)

Code locally with Mellum2.1 Thinking

Build a private AI agent with Kolibri 1

Create short video with audio using Kandinsky 6 Pro

Create a song locally with YuE2 3B

Create video locally with HunyuanVideo 1.5

Create a physical-AI scene with Cosmos3 Super

Set up private desktop chat with LFM3-1.7B Uncensored

Set up private phone chat with LFM3-1.7B Uncensored

Build a local coding assistant with MiniCPM5 2B SFT

openbmb/MiniCPM5-2B-GGUF

Chat privately with uncensored Gemma 4 E4B

Build a coding assistant with GLM 5.2 on rented GPUs

LFM2.5 2.6B local agent setup

Chat privately with Nemotron 3 Nano Omni

Build a local AI agent with Ministral 3 Reasoning

Chat locally with MiniCPM5 · 2B

MiniCPM5 2B local coding assistant metadata plan

Animate images locally with Wan2.1

Transcribe audio locally with Whisper large-v3-turbo

Generate speech locally with Kokoro-82M

Generate music locally with ACE-Step 1.5

Build private search with Qwen3 Embedding

Improve local search with Qwen3 Reranker

Create images on a rented GPU with SDXL Turbo

Turn your computer into a private AI server with ODS

Run open-source AI apps with Pinokio

Control your Android TV with AI using OmarchyTV