bartowski / MiniCPM5-2B-GGUF

Llamacpp imatrix Quantizations of MiniCPM5-2B by openbmb

Using llama.cpp release b10883 for quantization.

Original model: https://huggingface.co/openbmb/MiniCPM5-2B

Model details:

• Parameter count: 3B
• Input support: text
• Speculative decoding: no
• imatrix: yes - details

How to run

Prompt format

<s><|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Don't know which to choose? Grab Q4_K_M (1.62GB) - usually a good mix of size and performance. Download instructions available here

Available files:

Download a specific file:

hf download bartowski/MiniCPM5-2B-GGUF --include "MiniCPM5-2B-Q4_K_M.gguf" --local-dir ./

Downloading using the Hugging Face CLI

pip install -U "huggingface_hub[cli]"

hf download bartowski/MiniCPM5-2B-GGUF --include "MiniCPM5-2B-Q4_K_M.gguf" --local-dir ./

How to run

These quants run with llama.cpp - installable in one line via llama.app :

curl -LsSf https://llama.app/install.sh | sh
llama-server -hf bartowski/MiniCPM5-2B-GGUF:Q4_K_M

llama-server includes a built-in chat web UI, served at http://localhost:8080 by default.

These quants were made with llama.cpp release b10883 - if this model's architecture is newly supported, you'll need that release or newer to run them.

They also work in: LM Studio · koboldcpp · ramalama · Jan AI · Text Generation Web UI · LoLLMs · Atomic Chat

Per-tensor layouts

Some of these files were built with a layout computed for this model instead of llama.cpp's standard one-size-fits-all rules. A Q4_K_M is still mostly Q4_K; the extra precision goes to the weights this particular model is most sensitive to. The S, M or L in a name says how much of the model stays at the base precision: about 90 % for S, 70 % for M and 50 % for L. An _L name is simply the large size of its family. Q4_K_L is to Q4_K_M what Q4_K_M is to Q4_K_S, and Q6_K_L sits about halfway between Q6_K and Q8_0. In earlier releases an _L name meant the embedding and output weights were kept at Q8_0; in these files it means the larger size of the base type. There is no size target, so each file's bits per weight is reported rather than promised.

The layout each of these files was built with is published in the layouts/ folder: <file>.tensor-types.txt is the exact --tensor-type-file given to llama-quantize , and <file>.layout.json records how it was computed, including the generator version, the llama.cpp release and the commit, so any of them can be rebuilt.

Checked on this model before any of these files were released: Q4_K_M reached 0.94×, Q3_K_M 0.69× and IQ2_M 0.65× the KL divergence of the standard layout at the same file size.

imatrix

All quants made using imatrix option with dataset from here . The imatrix is available here: MiniCPM5-2B-imatrix.gguf .

ARM/AVX information

llama.cpp automatically "repacks" weights into an interleaved layout at load time for faster inference on ARM and AVX machines - details in this PR . This once required downloading special Q4_0_4_4/4_8/8_8 files; those are long gone. Online repacking now covers Q4_0, IQ4_NL, and most K-quants, so no special quant choice is needed for CPU inference.

Which file should I choose?

Credits

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.

Thank you ZeroWw for the inspiration to experiment with embed/output.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski