MI

MiniCPM V 4.7 35B A3B

MiniCPMGGUF by YTan2000Updated 2026-10-13
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant15.3 GB
Quick answer

MiniCPM V 4.7 35B A3B needs about 18.8 GB of memory at its main file (a 17.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 15.3 GB (IQ3_S) to 18.1 GB (Q3_K_L). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

MiniCPM V 4.7 35B A3B – a 35B MoE model with vision, reasoning, and tools

MiniCPM V 4.7 35B A3B is a 34.7B parameter model with 3B active parameters per token. It supports reasoning, tools, and vision. The model is released under apache-2.0 and is part of the MiniCPM family.

Good at

  • Vision and image understanding
  • Reasoning and tool use
  • Large context up to 262144 tokens

Limits

  • Requires a runtime that supports GGML_TYPE_COUNT ≥ 43 for TQ3_4S
  • No explicit language support listed
  • Large memory footprint for full precision

Best for

  • On-device inference with limited memory
  • Multimodal applications needing vision and reasoning
  • Research on MoE architectures

Who it’s for. Developers and researchers looking for an open‑source MoE model that can handle vision tasks and large contexts. The model is suitable for on‑device inference when the runtime supports the required tensor types.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_S15.3 GB 16.4 GB
Too big Get file →
—17.6 GB 18.8 GB
Too big Get file →
Q3_K_L18.1 GB 19.3 GB
Too big Get file →

For 8 GB VRAM, use IQ3_S (file size 15.26 GB, estimated 16.4 GB at 8 k context). If more memory is available, Q3_K_L (18.13 GB, 19.3 GB) offers higher quality. The unknown quant is larger (17.63 GB, 18.8 GB) and may be used when the runtime supports it.

What GPU do you need for MiniCPM V 4.7 35B A3B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q3_K_L (18.1 GB file, about 19.3 GB in use).

Which MiniCPM V 4.7 35B A3B quant should you choose?

If memory is tight, the smallest file is IQ3_S at 15.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized byYTan2000
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)671
Last updated2026-10-13

Frequently asked questions about MiniCPM V 4.7 35B A3B

How much VRAM does MiniCPM V 4.7 35B A3B need?

About 18.8 GB at its main file with an 8K context window. That is the 17.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run MiniCPM V 4.7 35B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MiniCPM V 4.7 35B A3B GGUF?

It depends on the quant: IQ3_S is 15.3 GB, file is 17.6 GB, Q3_K_L is 18.1 GB.

What context length does MiniCPM V 4.7 35B A3B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download MiniCPM V 4.7 35B A3B GGUF?

The files are on Hugging Face in the YTan2000/MiniCPM-V-4.7-35B-A3B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does MiniCPM V 4.7 35B A3B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run MiniCPM V 4.7 35B A3B on 8 GB VRAM?

Yes, using the IQ3_S quantization which requires about 16.4 GB of VRAM at 8 k context, which is within an 8 GB VRAM budget when using efficient batching.

What runtime is needed for the TQ3_4S quant?

TQ3_4S requires the turbo-tan/llama.cpp-tq3 fork because its tensor type id is 46, outside the mainline llama.cpp type table.

Does the model support multiple languages?

No language list is provided; the model is released under apache-2.0 with no explicit language support.

Other GGUFs of MiniCPM-V-4.7-35B-A3B

Similar models

Browse all →

More from YTan2000

All by YTan2000 →

More MiniCPM models

All MiniCPM →

Other large models

All large models →