Models/Mistral Small 4 · 119B

Coding / Mistral AI

Mistral Small 4 · 119B

Mistral Small 4 119B A6B is an Apache-2.0 licensed hybrid model from mistralai that combines general instruction, reasoning, and Devstral-style capabilities in one model. It uses a Mixture-of-Experts architecture with 119B total parameters, 6.5B activated per token, 128 experts with 4 active, and a 256k context length. It supports multimodal input (text and image) with text output, multilingual support across dozens of languages, system prompts, function calling, JSON output, and configurable reasoning effort. The model card also mentions optional efficiency resources: an eagle head for speculative decoding and an NVFP4 checkpoint. It is tagged for vLLM and offered in safetensors format.

Verified sourceRepository opened Jan 23, 2026Source checked 9/25/2026Version: a11f36be

LOCALRENTED GPUOPEN WEIGHTS

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

Popularity 62 out of 100. 29,619 downloads in 30 days; 472 lifetime likes. Checked Nov 7, 2026. Measures adoption, not quality.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source

Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Nov 8, 2026. Statistics checked Nov 7, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

WORKFLOWS FOR THIS MODEL 1

What do you want to do?

Choose a task. Get the software, files, settings, and steps to run it.

MAKE IT PERSONALChoose your hardware

Coding

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.

VS CodeCline

1 packageLinux

Open coding guide

Open a guide for its software, hardware requirements, and setup steps.

At a glance

Parameters: 119B total · 6.5B active
Architecture: Mixture of experts
Context length: 262,144
License: Apache 2.0
Disk space: 112.6 GB
Software: vLLM

MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

General chat assistant
Document parsing and extraction
Coding agent
Research assistant
Customization and fine-tuning

Tradeoffs

The provided source data does not include hardware requirements or compatibility details.
No specific performance benchmarks or test results are provided in the source data beyond vendor comparative claims.
The model's output modality is text only; image output is not supported.
Specific constraints of the 256k context window, such as effective context retention or degradation, are not described.
Details about latency, throughput, or resource usage for deployment are not provided beyond the model card's efficiency claims.

Ways to run it

vLLM · Linux

Repository-specific example documented in the publisher model card; confirm dependencies and platform in the source.

vllm serve mistralai/Mistral-Small-4-119B-2603 --max-model-len 262144 --tensor-parallel-size 2 --attention-backend FLASH_ATTN_MLA  --tool-call-parser mistral --enable-auto-tool-choice --reasoning-parser mistral --max_num_batched_tokens 16384 --max_num_seqs 128  --gpu_memory_utilization 0.8

Official instructions

Explore its uses

SAFETENSORSCODINGREASONINGAGENTSMULTIMODAL

REFERENCE LIBRARY

Sources and files

Primary sources and files behind this model page.

1 SOURCE

01Publisher model card and vLLM instructionshuggingface.co

Keep exploring

Coding

Qwen

Qwen2.5 Coder · 7B

Code generation, repair, and reasoning in a compact open-weight coding model.

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

Qwen3-Coder-Next · 80B A3B

Qwen3-Coder-Next is an open-weight text-generation model from Qwen/Qwen3-Coder-Next, licensed under apache-2.0. It is designed specifically for coding agents and local development. The model has 80B total parameters with 3B activated parameters, a 262,144-token native context length, and a hybrid architecture combining Gated DeltaNet, Gated Attention, and Mixture-of-Experts layers. It supports only non-thinking mode and does not generate thinking blocks.

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

MODEL SIZE80B total / 3B active

LOCALRENTED GPU

Repository opened Jan 30, 2026

Coding

JetBrains

Mellum2.1 Thinking

A 12B-total, 2.5B-active open-weight thinking model for coding and tool use. Start with JetBrains’ official GGUF on a suitable desktop, or serve the BF16 checkpoint with vLLM on a larger GPU.

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

MODEL SIZE12B total · 2.5B active

LOCALRENTED GPU

Released Sep 20, 2026