bartowski / dots-studio_dots3-note-prev-GGUF

Llamacpp imatrix Quantizations of dots3-note-prev by dots-studio

Using llama.cpp release b10569 for quantization.

Original model: https://huggingface.co/dots-studio/dots3-note-prev

Model details:

• Parameter count: 288B
• Input support: text
• Speculative decoding: yes (MTP) - details
• imatrix: yes - details

How to run

Prompt format

<|system|>{system_prompt}<|endofsystem|><|user|>{prompt}<|endofuser|><|assistant|>

Don't know which to choose? Grab Q4_K_M (171.11GB) - usually a good mix of size and performance. Download instructions available here

Available files:

Download a specific file:

hf download bartowski/dots-studio_dots3-note-prev-GGUF --include "dots-studio_dots3-note-prev-Q4_K_M/*" --local-dir ./

Downloading using the Hugging Face CLI

pip install -U "huggingface_hub[cli]"

hf download bartowski/dots-studio_dots3-note-prev-GGUF --include "dots-studio_dots3-note-prev-Q4_K_M/*" --local-dir ./

hf download bartowski/dots-studio_dots3-note-prev-GGUF --include "dots-studio_dots3-note-prev-Q8_0/*" --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/dots-studio_dots3-note-prev-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 b10569 - 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

MTP

This model has MTP (Multi-Token Prediction) layers, and they are included in these quants

MTP layers act as a built-in draft model, letting llama.cpp run speculative decoding for faster generation. To use them, add the following flag to your llama.cpp command:

--spec-type draft-mtp

Note: the MTP layers are stored at Q4_0 in the imatrix quants (except for the Q8_0 quant), since imatrix calibration does not exercise them. Q4_0 is chosen for its speed which massively benefits MTP performance.

imatrix

All quants made using imatrix option with dataset from here . The imatrix is available here: dots-studio_dots3-note-prev-imatrix.gguf .

Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

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