---
title: MiniCPM-V-4.7-35B-A3B-DSpark-gguf
canonical_url: "https://www.modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf"
md_url: "https://www.modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf.md"
repository: OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf
last_updated: 2026-10-14
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
base_model:
  - openbmb/MiniCPM-V-4.7-35B-A3B-DSpark
base_model_relation: quantized
library_name:
  - gguf
language:
  - en
  - zh
downloads: 34
stars: 0
tags:
  - minicpmv
  - minicpmv4.7
  - text-generation
  - vision-understanding
  - tool-calling
  - on-device
  - edge-ai
  - gguf
---

# MiniCPM-V-4.7-35B-A3B-DSpark-gguf

> MiniCPM-V-4.7-35B-A3B-DSpark-gguf - OpenBMB 在 ModelScope 开源的模型。This repository hosts the GGUF (llama.cpp) quantized version of MiniCPM-V-4.7-35B-A3B-DSpark. For the original BF16 weights and the full model card, please refer to…

OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf 是 ModelScope 魔搭社区上的text-generation模型，采用 apache-2.0 许可，基于 openbmb/MiniCPM-V-4.7-35B-A3B-DSpark 构建。

- **Repository**: OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf
- **License**: apache-2.0
- **Tasks**: text-generation
- **Base model**: openbmb/MiniCPM-V-4.7-35B-A3B-DSpark
- **Tags**: minicpmv, minicpmv4.7, text-generation, vision-understanding, tool-calling, on-device, edge-ai, gguf
- **Downloads**: 34
- **Stars**: 0
- **Last updated**: 2026-10-14

Source: https://www.modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf

---

> **This repository hosts the GGUF (llama.cpp) quantized version of [MiniCPM-V-4.7-35B-A3B-DSpark](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B-DSpark).** For the original BF16 weights and the full model card, please refer to [openbmb/MiniCPM-V-4.7-35B-A3B-DSpark](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B-DSpark).


# MiniCPM-V-4.7-35B-A3B-DSpark

`MiniCPM-V-4.7-35B-A3B-DSpark` is a [DSpark](https://arxiv.org/abs/2607.05147) draft checkpoint trained for exact pairing with [MiniCPM-V-4.7-35B-A3B](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B) and its tokenizer.

## Model Specification


| Property                      | Value                                                                         |
| ----------------------------- | ----------------------------------------------------------------------------- |
| Target model                  | [MiniCPM-V-4.7-35B-A3B](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B) |
| Draft layers                  | 5                                                                             |
| Draft parameters              | 389,223,169                                                                   |
| Draft tokens per forward pass | 15                                                                            |
| Target hidden-state layers    | `[3, 11, 19, 27, 35]`                                                         |
| Checkpoint precision          | BF16                                                                          |


## Training Recipe

Training responses were generated by [MiniCPM-V-4.7-35B-A3B](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B) from a mixture of Vision & Text prompts.


| Setting            | Value                     |
| ------------------ | ------------------------- |
| Training sequences | 2M                        |
| Epochs             | 6                         |
| Optimizer          | AdamW                     |
| Objective          | CE + L1 + confidence loss |




## Evaluation

Acceptance length is defined as the total number of completion tokens divided by the total number of speculative verification steps. Evaluation uses natural EOS termination and `max_new_tokens=8192`.


| **Domain**            | **Accept Length** | 
| --------------------- | ----------------- |
| **Vision**            |                   |
| MMMU                  | 5.098             |
| MathVista             | 6.126             |
| CharXiv_reasoning_val | 5.479             |
| OCRBench              | 5.407             |
| **Text**              |                   |
| Math                  | 6.687             |
| Code                  | 7.387             |
| General               | 3.501             |




## Usage with vLLM

```bash
vllm serve \
  --model openbmb/MiniCPM-V-4.7-35B-A3B \
  --served-model-name MiniCPM-V-4.7-35B-A3B \
  --tensor-parallel-size 2 \
  --max-model-len 40960 \
  --max-num-batched-tokens 40960 \
  --max-num-seqs 1 \
  --attention-backend FLASH_ATTN \
  --mm-encoder-attn-backend FLASH_ATTN \
  --mm-processor-kwargs '{"downsample_mode":"4x"}' \
  --trust-request-mm-kwargs \
  --disable-custom-all-reduce \
  --compilation-config '{"pass_config":{"fuse_allreduce_rms":false}}' \
  --speculative-config '{"method":"dspark","model":"openbmb/MiniCPM-V-4.7-35B-A3B-DSpark","num_speculative_tokens":15,"enable_adaptive_verification":false}' \
  --default-chat-template-kwargs '{"enable_thinking":false}'
```



## Usage with llama.cpp

Download the target model, its vision projector (`mmproj`), and this DSpark draft:

```bash
huggingface-cli download openbmb/MiniCPM-V-4.7-35B-A3B-gguf MiniCPM-V-4_7-35B-A3B-Q4_K_M.gguf mmproj-model-f16.gguf --local-dir ./35B-A3B-gguf
huggingface-cli download openbmb/MiniCPM-V-4.7-35B-A3B-DSpark-gguf dspark-MiniCPM-V-4_7-35B-A3B-Q8_0.gguf --local-dir ./35B-A3B-gguf
```

Run with speculative decoding (`-md` = draft, `--spec-type draft-dspark`). `llama-cli` handles **both** the vision projector and the draft:

```bash
llama-cli \
  -m ./35B-A3B-gguf/MiniCPM-V-4_7-35B-A3B-Q4_K_M.gguf \
  --mmproj ./35B-A3B-gguf/mmproj-model-f16.gguf \
  -md ./35B-A3B-gguf/dspark-MiniCPM-V-4_7-35B-A3B-Q8_0.gguf \
  --spec-type draft-dspark \
  --image image.jpg -p "Describe this image." \
  -ngl 99 -ngld 99 -fa on -c 8192
```

For a multimodal server:

```bash
llama-server \
  -m ./35B-A3B-gguf/MiniCPM-V-4_7-35B-A3B-Q4_K_M.gguf \
  --mmproj ./35B-A3B-gguf/mmproj-model-f16.gguf \
  -md ./35B-A3B-gguf/dspark-MiniCPM-V-4_7-35B-A3B-Q8_0.gguf \
  --spec-type draft-dspark --spec-draft-n-max 15 \
  -ngl 99 -ngld 99 -fa on -c 8192 --jinja --port 8080
```

Requires a llama.cpp build with the `dflash` architecture and the DSpark Markov head. The draft must be paired with the matching MiniCPM-V 4.7 35B-A3B target. Draft quantization only affects acceptance length (never the output), so pick the smallest quant that fits — `Q8_0` / `Q6_K` are good defaults.

## Limitations and Disclaimer

This model has no autonomous intent or legal personhood; its outputs are text generated from statistical patterns and may be inaccurate, biased, or offensive, and may be manipulated by carefully crafted prompts ("jailbreaks") into producing unintended content. Its responses on sensitive topics such as politics, health, finance, and law are not reviewed by experts and should not be treated as professional advice.

This model is provided "**AS IS**", without warranty of any kind, express or implied, and the developers are not liable for any damages arising from its use. Users must employ the model only for lawful, compliant, and ethical purposes, configure their own safeguards, and label AI-generated content where required; deliberate jailbreaking, injection attacks, or inducing harmful output is prohibited, and any such testing is at the user's own risk.