Model reference · open weights
MiniCPM5-DSpark is an open-weight language model from openbmb. MiniCPM5-2B-DSpark-GGUF (GGUF) weighs 653 MB; the smallest configuration that runs it is RTX 3060 12 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the openbmb/MiniCPM5-2B-DSpark-GGUF model card, 2026-10-01
What it is
| Released by | openbmb |
|---|---|
| Released | 2026-09-09 |
| VRAM | 653 MB for the weights |
What it runs on
How much memory each request adds isn't estimated yet for this architecture. The weights need at least the cards below, plus room for the context.
| Card | Weights alone |
|---|---|
| RTX 3060 12 GB | fits |
| RTX 4060 Ti 16 GB | fits |
| RTX 3090 24 GB | fits |
| RTX 4090 24 GB | fits |
| RTX 5090 32 GB | fits |
| L40S 48 GB | fits |
| A100 80 GB | fits |
| H100 80 GB | fits |
| RTX PRO 6000 Blackwell 96 GB | fits |
| DGX Spark (GB10) 128 GB unified | fits |
| H200 141 GB | fits |
| B200 180 GB | fits |
Builds
| Build | Params | Precision | Weights | Smallest setup |
|---|---|---|---|---|
| MiniCPM5-2B-DSpark-GGUF (above) ↗ | GGUF | 653 MB | RTX 3060 12 GB | |
| MiniCPM5-2B-DSpark ↗ | 324M | BF16 | 648 MB | RTX 3060 12 GB |
From the model card
GGUF version of MiniCPM5-2B-DSpark for speculative decoding with MiniCPM5-2B in llama.cpp.
| File | Precision | Size |
|---|---|---|
MiniCPM5-2.6B-DSpark.gguf | BF16 | 653 MB |
llama-server \
-m MiniCPM5-2B-Q4_K_M.gguf \
-md MiniCPM5-2.6B-DSpark.gguf \
--spec-type draft-dspark --spec-draft-n-max 7 \
-ngl 99 -ngld 99 -fa on \
-c 8192 --jinja --port 8080
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.
This repository and MiniCPM model weights are released under the Apache-2.0 License.
Please cite our paper if you find our work valuable:
@article{minicpm4,
title={Minicpm4: Ultra-efficient llms on end devices},
author={MiniCPM, Team},
journal={arXiv preprint arXiv:2506.07900},
year={2025}
}
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works