MI

MiniCPM

MiniCPMGGUF by runfutureUpdated 2024-02-09
Download on Hugging Face
Parameters2.72B
Context2K
Layers40
Architectureminicpm
Smallest quant1.7 GB
Quick answer

MiniCPM needs about 5.2 GB of memory at its main file (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU.

MiniCPM 2.72B LLM in a single GGUF file

MiniCPM is a 2.72‑billion‑parameter language model. The GGUF file is 1.73 GB and requires about 5.2 GB of VRAM at 8 k context. It is a single‑model architecture with no mixture of experts.

Good at

  • Compact 2.72B size
  • Fast inference on modest GPUs
  • Easy deployment with llama.cpp

Limits

  • Requires 5.2 GB VRAM at 8 k context
  • No quant options listed
  • No license information provided

Best for

  • Local chatbot prototypes
  • Quick fine‑tuning experiments
  • Low‑cost inference on consumer GPUs

Who it’s for. Developers needing a small, fast LLM for local use. Suitable for hobbyists and researchers with limited GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.7 GB 3.0 GB
Fits Get file →

The only available quant is the default GGUF file. It uses 1.73 GB and needs 5.2 GB VRAM at 8 k context. No other quants are listed, so use this file if you have the required memory.

What GPU do you need for MiniCPM?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is the main file (1.7 GB file, about 5.2 GB in use).

Specifications

Architecture from the GGUF header

Architectureminicpm
Parameters2.72B
Layers40
Trained context2,048 tokens
KV cache (fp16)360 KB per token

Source

Quantized byrunfuture
FamilyMiniCPM
Downloads (HF)2,360
Last updated2024-02-09

Frequently asked questions about MiniCPM

How much VRAM does MiniCPM need?

About 5.2 GB at its main file with an 8K context window. That is the 1.7 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 MiniCPM on an 8 GB GPU?

Yes, with the smaller files: the 1.7 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM GGUF?

It depends on the quant: file is 1.7 GB.

What context length does MiniCPM support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 3.0 GB at 8K and 0.8 GB at 2K.

Where can I download MiniCPM GGUF?

The files are on Hugging Face in the runfuture/MiniCPM-2B-dpo-q4km-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run MiniCPM on 8 GB VRAM?

The model needs about 5.2 GB VRAM at 8 k context, so 8 GB is sufficient for inference.

Does MiniCPM support vision?

No vision support is indicated in the provided facts.

What quantization is available for MiniCPM?

Only the default GGUF file is listed; no other quant options are provided.

Similar models

Browse all →

More from runfuture

All by runfuture →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →