Get the latest setups
Models/MiniCPM5/MiniCPM5 2B Midtrain
Text / openbmb

MiniCPM5 2B Midtrain

MiniCPM5 2B Midtrain is the second model in the MiniCPM5 series, a dense 2B Transformer from OpenBMB built for on-device, local deployment, and resource-constrained scenarios. It scales up the same training recipe used for MiniCPM5-1B and is released under the apache-2.0 license. The model card describes it as reaching 2B-class open-source SOTA within its comparison set and remaining competitive with 4B-class models overall, with reported advantages over comparable-size models in coding, mathematics, long-context understanding, tool use, and agentic tasks. Languages listed are English and Chinese, and the model is associated with the transformers library and text-generation pipeline. Training data includes openbmb Ultra-FineWeb, UltraX-Preview, Ultra-FineWeb-L3, UltraData-Math, UltraData-Code, UltraData-SFT-2605, UltraData-SFT-Agent-2609, and UltraData-RL-2609.

EstimatedRepository opened Sep 1, 2026Source checked 9/24/2026Version: 0a45344e
LOCALRENTED GPUOPEN WEIGHTS
Freshness 84 out of 100. Repository age: 44 days old, Sep 1, 2026. Measures age, not quality.
Popularity 47 out of 100. 4,225 downloads in 30 days; 22 lifetime likes. Checked Oct 15, 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 Oct 15, 2026. Statistics checked Oct 15, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

At a glance

Parameters
2.52B
Architecture
llama
Context length
131,072
License
apache-2.0
Disk space
4.7 GB
Software
llama.cpp, SGLang, vLLM
View the model source
MY HARDWARE

Will it run on your machine?

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

Add my hardware

Best for

  • On-device or local text generation in resource-constrained settings.
  • Coding-related tasks.
  • Mathematics-related tasks.
  • Long-context understanding.
  • Tool use and agentic tasks.

Tradeoffs

  • Dense 2B Transformer only; no larger variants are described in the supplied facts.
  • Model card languages are limited to English and Chinese.
  • No numerical hardware requirements are provided in the source data.
  • No compatibility, performance benchmarks, or testing results are provided in the source data.
  • Dataset details are listed only as names; no licensing, quality, or content limitations of datasets are provided.

Ways to run it

llama.cpp · Windows, macOS, Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

llama-server -m MiniCPM5-2B-F16.gguf -a MiniCPM5-2B --port 8080 -ngl 99 -c 8192 --jinja
Official instructions

SGLang · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

python -m sglang.launch_server --model-path openbmb/MiniCPM5-2B --port 30000
Official instructions

vLLM · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

vllm serve openbmb/MiniCPM5-2B --port 8000
Official instructions

Explore its uses

SAFETENSORSTEXT-GENERATION

Keep exploring

Text
Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

Freshness 90 out of 100. Release age: 28 days old, Sep 17, 2026. Measures age, not quality.
Popularity 90 out of 100. 4,849,199 downloads in 30 days; 2,697 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
MODEL SIZE27.36B
LOCALRENTED GPU
Released Sep 17, 2026
Text
DeepSeek

DeepSeek V4.1 Flash

A multimodal reasoning model with a compressed key-value cache, published as open weights.

Freshness 87 out of 100. Repository age: 35 days old, Sep 10, 2026. Measures age, not quality.
Popularity 84 out of 100. 1,238,583 downloads in 30 days; 4,519 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
Arena Open Source Text: rank 5 of 225. Ranked model: deepseek-v4.1-flash-max. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.+3
LOCALRENTED GPU
Repository opened Sep 10, 2026
Text
Qwen

Qwen3.8

Explore 4 versions of Qwen3.8. Compare model sizes, packages, hardware requirements, and available setups.

4 versionsCompare sizes & formats
LOCALRENTED GPU
Compare versions →