MI

MiniCPM V 4.7 35B A3B DSpark

MiniCPMGGUF by magnitudedevUpdated 2026-10-13
Download on Hugging Face
Parameters389M
Context256K
Layers5
Architecturedflash
Smallest quant0.4 GB
Quick answer

MiniCPM V 4.7 35B A3B DSpark needs about 1.0 GB of memory at Q8_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.

MiniCPM V 4.7 35B A3B DSpark – a draft model with vision, reasoning, and tool use

MiniCPM V 4.7 35B A3B DSpark is a draft checkpoint designed to pair with MiniCPM V 4.7 35B A3B. It supports vision, reasoning, and tool usage. The model is built on the dflash architecture and trained with a 262144 token context.

Good at

  • Vision and text reasoning
  • Tool invocation
  • Bidirectional draft attention

Limits

  • Requires target model and DSpark runtime
  • No autonomous intent or legal personhood
  • Not a standalone language model

Best for

  • Drafting and verifying text outputs
  • Vision‑enabled prompt generation
  • Tool‑based workflow integration

Who it’s for. Developers building applications that need a draft model for text and vision tasks. The model is intended for use with the MiniCPM V 4.7 35B A3B and a runtime that supports DSpark.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.4 GB 1.0 GB
Fits Get file →

The only available quantization is Q8_0. The file size is 0.42 GB and it requires approximately 1 GB of VRAM at an 8 k context length. For larger VRAM budgets, this quant is suitable; for smaller budgets, a different model is recommended.

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 Q8_0 (0.4 GB file, about 1.0 GB in use).

Which MiniCPM V 4.7 35B A3B DSpark quant should you choose?

Q8_0 (0.4 GB) is the middle option in this repository. 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

Architecturedflash
Parameters389M
Layers5
Trained context262,144 tokens
KV cache (fp16)10 KB per token

Source

Quantized bymagnitudedev
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)1,230
Last updated2026-10-13

Frequently asked questions about MiniCPM V 4.7 35B A3B DSpark

How much VRAM does MiniCPM V 4.7 35B A3B DSpark need?

About 1.0 GB at Q8_0 with an 8K context window. That is the 0.4 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 Q8_0: the 0.4 GB file needs about 1.0 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: Q8_0 is 0.4 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 magnitudedev/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 Q8_0 quant requires about 1 GB of VRAM at an 8 k context length, leaving ample headroom in an 8 GB VRAM setup.

Does this model support vision tasks?

Yes, the model has detected vision ability and is designed for vision and text prompts.

Is this model a standalone language model?

No, it requires the corresponding target model and a runtime with DSpark support to function.

Other GGUFs of MiniCPM-V-4.7-35B-A3B-DSpark

Similar models

Browse all →

More from magnitudedev

All by magnitudedev →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →