LocalClaw/LLM/MiniCPM5 2B
Open-weight local LLM

MiniCPM5 2B

Catalogue summary: Official OpenBMB compact on-device LLM with Apache 2.0 licensing, 131K context, tool-calling and coding focus, plus official Q4_K_M GGUF, Ollama, llama.cpp, Docker and OpenClaw run paths.

Repository editorial metadata; verify comparative claims in the linked upstream material.

4 GB catalogue minimum4 GB RAMQ4_K_MCoding assistant
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models
Open in LM StudioOpens the app on this model's download screenOpen in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens the model filesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
2B
Minimum RAM
4 GB
Model size
1.6 GB
Quantization
Q4_K_M

Can MiniCPM5 2B run locally?

MiniCPM5 2B has a catalogue minimum of 4 GB RAM with Q4_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use minicpm5-2b as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Model sourcePublic GGUF repository (verified 2026-09-07): openbmb/MiniCPM5-2B-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningagentlightlong-contexttool-callinggeneral

Install path

01
Check RAM fitMinimum 4 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch minicpm5-2b in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: minicpm
  • Parameters: 2B
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 4 GB
  • Catalogue model size: 1.6 GB
  • Tags: chat, code, reasoning, agent, light, long-context, tool-calling, general

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • reasoning
  • agent
  • light
  • long-context

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
10
quality
7
coding
7
reasoning
7

Technical notes

Developer
OpenBMB (Tsinghua)
License
Apache 2.0
Context window
131,072 tokens
Architecture
Dense MiniCPM5 decoder-only language model with 2.5B total parameters, 42 layers, grouped-query attention and long-context/tool-calling oriented post-training.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Entry laptop fitMacBook Air 8GBMore headroomMac mini M4 16GBAll compatible picks8GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

MiniCPM5 1B 1BMiniCPM-V (8B) 8BNanbeige4.2 3B 4B (3B non-embedding)Spark-X2.5-1.7B 1.7BGranite 4.1 (3B) 3BAgents-A1 4B 4BGranite 4.2 (3B) 3BK2-Horizon-0.9B 0.9B

Where to go next