MiniCPM V 4.7 35B A3B DSpark needs about 0.8 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 11 quants, from 0.2 GB (Q4_0) to 0.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.
MiniCPM V 4.7 35B A3B DSpark – a 0.4B parameter vision‑text draft model
MiniCPM V 4.7 35B A3B DSpark is a 0.4 billion‑parameter draft checkpoint trained on a mixture of vision and text prompts. It is designed to pair with the MiniCPM‑V‑4.7‑35B‑A3B target model and supports speculative decoding via the dflash architecture.
Good at
- Vision‑text multimodal inference
- Speculative decoding with draft‑dspark
- Tool‑use prompts
Limits
- No autonomous intent or legal personhood
- Requires dflash architecture and DSpark Markov head
- No built‑in safety guardrails
Best for
- Rapid prototyping of vision‑text pipelines
- Testing speculative decoding strategies
- Research on draft‑dspark models
Who it’s for. Developers and researchers who need a lightweight draft model for vision‑text tasks and want to experiment with speculative decoding. The model is suitable for local deployment with llama.cpp and a compatible vision projector.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q4_1 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q5_0 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_S | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_1 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| F16 | 0.8 GB | 1.4 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0, Q4_K_S, or Q4_K_M – each is 0.23 GB and needs about 0.8 GB at 8 k context. For 12 GB VRAM, Q5_0, Q5_K_S, or Q5_K_M (0.28 GB, ~0.9 GB) are suitable. For higher precision, Q8_0 (0.42 GB, ~1 GB) or F16 (0.79 GB, ~1.4 GB) can be used if memory allows.
What GPU do you need for MiniCPM V 4.7 35B A3B DSpark?
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 F16 (0.8 GB file, about 1.4 GB in use).
Which MiniCPM V 4.7 35B A3B DSpark quant should you choose?
Q4_K_M is the usual starting point for MiniCPM V 4.7 35B A3B DSpark: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.4 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q4_0 at 0.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
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 DSpark
How much VRAM does MiniCPM V 4.7 35B A3B DSpark need?
About 0.8 GB at Q4_K_M with an 8K context window. That is the 0.2 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 DSpark on an 8 GB GPU?
Yes, with F16: the 0.8 GB file needs about 1.4 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 DSpark GGUF?
It depends on the quant: Q4_0 is 0.2 GB, Q4_K_S is 0.2 GB, Q4_K_M is 0.2 GB, Q4_1 is 0.3 GB, Q5_0 is 0.3 GB, Q5_K_S is 0.3 GB and 5 more.
What context length does MiniCPM V 4.7 35B A3B DSpark 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 DSpark GGUF?
The files are on Hugging Face in the openbmb/MiniCPM-V-4.7-35B-A3B-DSpark-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 DSpark 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 DSpark on 8 GB VRAM?
Yes, the Q4_0, Q4_K_S, or Q4_K_M quantizations are 0.23 GB each and require about 0.8 GB at 8 k context, fitting within 8 GB VRAM.
Does this model support vision input?
Yes, it has detected vision ability and is trained on vision and text prompts.
What is the maximum context length?
The model was trained with 262,144 context tokens.