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 3 quants, from 0.2 GB (Q4_K_M) to 0.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.
MiniCPM V 4.7 35B A3B DSpark – a lightweight draft model for speculative decoding
MiniCPM V 4.7 35B A3B DSpark is a draft checkpoint designed to accelerate inference via speculative decoding. It pairs with MiniCPM-V 4.7 35B-A3B and supports vision prompts. The model is 0.389 billion parameters and trained on 262144 context tokens.
Good at
- Vision prompt handling
- Speculative decoding acceleration
- Compatible with MiniCPM-V 4.7 35B-A3B
Limits
- Requires pairing with MiniCPM-V 4.7 35B-A3B
- No autonomous intent or legal personhood
- Memory usage increases with larger context
Best for
- Vision‑text hybrid tasks
- Rapid inference with draft models
- Low‑latency applications
Who it’s for. Developers needing a fast draft model for vision‑text tasks. Researchers testing speculative decoding with MiniCPM-V 4.7 35B-A3B.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| BF16 | 0.8 GB | 1.4 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.24 GB file, ~0.8 GB memory at 8 k context). If 12 GB VRAM is available, Q8_0 (0.42 GB file, ~1 GB memory) offers higher precision. BF16 (0.79 GB file, ~1.4 GB memory) is best when sufficient VRAM exists.
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 BF16 (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.
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 BF16: 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_K_M is 0.2 GB, Q8_0 is 0.4 GB, BF16 is 0.8 GB.
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 UserSuxx/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_K_M quantization requires about 0.8 GB memory at 8 k context, fitting within 8 GB VRAM.
Do I need a separate MiniCPM-V 4.7 35B-A3B model?
Yes, DSpark is a draft model and must be paired with MiniCPM-V 4.7 35B-A3B for inference.
What license applies to this model?
The model is licensed under Apache-2.0.