MI

MiniCPM5 2B DSpark

MiniCPMGGUF by openbmbUpdated 2026-09-09
Download on Hugging Face
Parameters324M
Context128K
Layers5
Architecturedflash
Smallest quant0.7 GB
Quick answer

MiniCPM5 2B DSpark needs about 1.2 GB of memory at its main file (a 0.7 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 0.2 GB.

MiniCPM5 2B DSpark – lightweight 2B‑parameter model for coding and tool use

MiniCPM5 2B DSpark is a 0.324 billion‑parameter dflash architecture model. It supports up to 131 072 context tokens and is optimized for speculative decoding in llama.cpp. The model is released under Apache‑2.0 and contains no autonomous intent.

Good at

  • Coding tasks
  • Tool‑based interactions
  • Long‑context generation

Limits

  • No vision support
  • Requires 8 k context for memory estimate
  • License is Apache‑2.0

Best for

  • Developers building lightweight code assistants
  • Researchers testing long‑context models
  • Embedded LLM deployments

Who it’s for. This model is suited for developers and researchers who need a small, efficient LLM capable of handling long contexts and coding tasks. It is ideal for local deployments where GPU memory is limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.7 GB 1.2 GB
Fits Get file →

The provided GGUF file is 0.65 GB and requires approximately 1.2 GB of VRAM at 8 k context. For 8 GB VRAM, the default quant is suitable. If memory is tighter, consider a higher‑compression quant if available, but no other quants are listed.

What GPU do you need for MiniCPM5 2B 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 the main file (0.7 GB file, about 1.2 GB in use).

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters324M
Layers5
Trained context131,072 tokens
KV cache (fp16)5 KB per token

Source

Quantized byopenbmb
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)3,877
Last updated2026-09-09

Frequently asked questions about MiniCPM5 2B DSpark

How much VRAM does MiniCPM5 2B DSpark need?

About 1.2 GB at its main file with an 8K context window. That is the 0.7 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 MiniCPM5 2B DSpark on an 8 GB GPU?

Yes, with the smaller files: the 0.7 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 MiniCPM5 2B DSpark GGUF?

It depends on the quant: file is 0.7 GB.

What context length does MiniCPM5 2B DSpark support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.0 GB at 8K and 0.2 GB at 32K.

Where can I download MiniCPM5 2B DSpark GGUF?

The files are on Hugging Face in the openbmb/MiniCPM5-2B-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 MiniCPM5 2B 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 MiniCPM5 2B DSpark on 8 GB VRAM?

Yes, the 0.65 GB GGUF file needs about 1.2 GB VRAM at 8 k context, well within an 8 GB GPU.

Does this model support vision?

No, MiniCPM5 2B DSpark has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from openbmb

All by openbmb →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →