LocalClaw/LLM/MiniCPM-V 4.7 35B-A3B
Open-weight MoE

MiniCPM-V 4.7 35B-A3B

Use case: Reasoning. Check the memory fit and choose a setup path below.

32 GB catalogue minimum32 GB RAMQ4_K_MReasoning
Choose an app

This model needs a special runtime. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
UnslothNot available for this model
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloads
llama.cppNot available for this model
Use with LocalClawOptional workspace after the model is installed
This model needs its official runtimecurrent llama.cpp / Ollama MiniCPM-V 4.7 MoE support
Parameters
35B (3B active, MoE)
Minimum RAM
32 GB
Model size
19.71 GB
Quantization
Q4_K_M

About MiniCPM-V 4.7 35B-A3B

Catalogue summary: OpenBMB Apache 2.0 MiniCPM-V 4.7 MoE release with image, multi-image and video understanding. Official Q4_K_M GGUF is about 21.2GB for workstation-class local multimodal use.

MiniCPM-V 4.7 35B-A3B has a catalogue minimum of 32 GB RAM with Q4_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use the official current llama.cpp / Ollama MiniCPM-V 4.7 MoE support setup. The current low-bit files are not a stock LM Studio install.

Model sourcePublic GGUF repository (verified 2026-11-06): openbmb/MiniCPM-V-4.7-35B-A3B-ggufUpstream releasePaper or model cardLicence text
visionvideoreasoningpowermultimodalmoegeneral

Install path

01
Check RAM fitMinimum 32 GB RAM. Start with the Q4_K_M quant.
02
Load the modelFollow the official current llama.cpp / Ollama MiniCPM-V 4.7 MoE support instructions. Stock LM Studio support is not confirmed.
03
Try your workloadStart with a short prompt, check memory use and adjust context length before running longer tasks.

Catalogue record

  • Family: minicpm
  • Parameters: 35B (3B active, MoE)
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 32 GB
  • Catalogue model size: 19.71 GB
  • Tags: vision, video, reasoning, power, multimodal, moe, 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.

Reading the scores

LocalClaw /10 is an editorial catalogue rating. Community /5 comes from member reviews. Your machine fit is a separate memory and runtime assessment.

Capability profile

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

speed
6
quality
9
coding
5
reasoning
8

Technical notes

Developer
OpenBMB (Tsinghua)
License
Apache 2.0
Context window
262,144 tokens
Architecture
MiniCPM-V 4.7 multimodal MoE with 35B total parameters, about 3B active parameters, 256 experts, eight selected experts per token, early visual-token compression, mixed 4x/16x visual compression and a 262K text context configuration.

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.

Comfortable headroomMac mini M4 Pro 48GBMobile workstationMacBook Pro M4 Max 36GBPower-user picks32GB RAM guide

Related catalogue entries

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

MiniCPM-V 4.7 (1B) 1BMiniCPM5 1B 1BMiniCPM5 2B 2BMiniCPM-V (8B) 8BGemma 4 12B 12BAgents-A1 35B (3B active, MoE)DiffusionGemma 26B-A4B Instruct 26B (4B active, diffusion MoE)Gemma 4 26B A4B 26B (A4B active)

Where to go next