MiniCPM-V-4.7-35B-A3B needs about 18.8 GB of memory at IQ4_XS (a 17.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 10.1 GB (IQ2_XXS) to 36.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
MiniCPM‑V 4.7 35B‑A3B – a 35B‑parameter MoE vision‑LLM in GGUF format
MiniCPM‑V 4.7 35B‑A3B is a 35‑billion‑parameter mixture‑of‑experts model with 3 billion active experts. It supports single‑image, multi‑image, and video understanding. The model is released under Apache‑2.0 and can run on‑device with efficient quantizations.
Good at
- Vision‑enabled language tasks
- On‑device inference with low memory
- Fast decoding with Lookahead Expert Scheduling
Limits
- Requires at least 3 GB VRAM for best performance
- No text‑only mode without vision support
- Large context size may exceed VRAM on low‑end GPUs
Best for
- Mobile vision‑assistant apps
- Edge inference on ARM and Rockchip devices
- Low‑latency image captioning
Who it’s for. Developers building on‑device multimodal assistants or edge AI solutions that need a compact vision‑LLM. The model is suitable for iOS, Android, HarmonyOS, and various chip platforms with limited VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 10.1 GB | 11.3 GB | Too big | Get file → | |
| IQ2_XS | 11.3 GB | 12.5 GB | Too big | Get file → | |
| IQ2_S | 12.3 GB | 13.5 GB | Too big | Get file → | |
| IQ3_XXS | 13.7 GB | 14.8 GB | Too big | Get file → | |
| IQ3_S | 15.5 GB | 16.7 GB | Too big | Get file → | |
| IQ4_XS | 17.6 GB | 18.8 GB | Too big | Get file → | |
| Q4_K | 20.1 GB | 21.3 GB | Too big | Get file → | |
| Q5_K | 21.5 GB | 22.6 GB | Too big | Get file → | |
| Q5_K | 22.1 GB | 23.3 GB | Too big | Get file → | |
| Q6_K | 26.2 GB | 27.4 GB | Too big | Get file → | |
| Q6_K | 29.1 GB | 30.3 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → |
For 8 GB VRAM, the IQ2_XXS (10.14 GB) or IQ2_XS (11.32 GB) files are the smallest that fit, with estimated memory usage of 11.3 GB and 12.5 GB at 8 k context. If 12 GB VRAM is available, IQ2_S (12.32 GB) offers a balance of size and quality. Higher‑quality Q4_K or Q5_K variants require 20–22 GB VRAM.
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: the best quant that fits is IQ2_XXS (10.1 GB file, about 11.3 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XXS (13.7 GB file, about 14.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K (22.1 GB file, about 23.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (29.1 GB file, about 30.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).
Which MiniCPM-V-4.7-35B-A3B quant should you choose?
IQ4_XS (17.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ2_XXS at 10.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
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 IQ4_XS 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 11.3 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: IQ2_XXS is 10.1 GB, IQ2_XS is 11.3 GB, IQ2_S is 12.3 GB, IQ3_XXS is 13.7 GB, IQ3_S is 15.5 GB, IQ4_XS is 17.6 GB and 6 more.
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 AtomicChat/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?
The smallest quantizations (IQ2_XXS or IQ2_XS) fit within 8 GB VRAM, but memory usage at 8 k context is approximately 11–12 GB, so a 8 GB GPU will be insufficient.
Does the model support text‑only inference?
The model is vision‑enabled and does not provide a dedicated text‑only mode; it requires image input for full functionality.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.