MiniCPM V 4.7 35B A3B ROCmFP4 needs about 20.4 GB of memory at its main file (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 0.6 GB (Q8_0) to 20.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.
MiniCPM V 4.7 35B A3B ROCmFP4 – 35B‑parameter MLLM with vision, reasoning and tools
MiniCPM V 4.7 35B A3B ROCmFP4 is a 34.7B‑parameter model in the MiniCPM family. It supports reasoning, tools and vision and is trained on 262144 context tokens. The model is released under the apache‑2.0 license.
Good at
- Vision and multimodal tasks
- Reasoning and tool use
- On‑device inference on AMD GPUs
Limits
- Requires 3 GB+ VRAM for full‑precision inference
- No dedicated vision‑only mode in the provided GGUFs
- No explicit support for other hardware platforms
Best for
- Edge inference on AMD GPUs
- Multimodal chat applications
- Tool‑enabled workflows
Who it’s for. Developers building multimodal applications on AMD hardware who need a large‑parameter model with vision, reasoning and tool capabilities. The model is suitable for on‑device inference where memory is limited but performance is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| — | 19.8 GB | 20.4 GB | Too big | Get file → | |
| — | 20.2 GB | 20.8 GB | Too big | Get file → |
For 8 GB VRAM, use the Q8_0 quantized file (0.57 GB, ~1.2 GB memory at 8 k context). If more memory is available, the larger unknown quant files (19.85 GB and 20.18 GB) provide higher fidelity but require ~20 GB memory at 8 k context. The estimates are approximate.
What GPU do you need for MiniCPM V 4.7 35B A3B ROCmFP4?
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: the best quant that fits is Q8_0 (0.6 GB file, about 1.2 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (0.6 GB file, about 1.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (0.6 GB file, about 1.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (0.6 GB file, about 1.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (0.6 GB file, about 1.2 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (20.2 GB file, about 20.8 GB in use).
Which MiniCPM V 4.7 35B A3B ROCmFP4 quant should you choose?
If memory is tight, the smallest file is Q8_0 at 0.6 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
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 ROCmFP4
How much VRAM does MiniCPM V 4.7 35B A3B ROCmFP4 need?
About 20.4 GB at its main file with an 8K context window. That is the 19.8 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 ROCmFP4 on an 8 GB GPU?
Yes, with Q8_0: the 0.6 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiniCPM V 4.7 35B A3B ROCmFP4 GGUF?
It depends on the quant: Q8_0 is 0.6 GB, file is 19.8 GB, file is 20.2 GB.
What context length does MiniCPM V 4.7 35B A3B ROCmFP4 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.3 GB at 32K.
Where can I download MiniCPM V 4.7 35B A3B ROCmFP4 GGUF?
The files are on Hugging Face in the kingjones777/MiniCPM-V-4.7-35B-A3B-ROCmFP4-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 ROCmFP4 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 on 8 GB VRAM?
Yes, the Q8_0 quantized file is 0.57 GB and requires about 1.2 GB of VRAM at 8 k context, which fits within 8 GB.
Does the model support vision tasks?
Yes, the model has detected vision ability and supports single‑image, multi‑image and video understanding.
What license applies to this model?
The model is released under the apache‑2.0 license.