RichardErkhov/leafspark_-_Pixtral-12B-2409-hf-text-only-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Pixtral-12B-2409-hf-text-only - GGUF

• Model creator: https://huggingface.co/leafspark/
• Original model: https://huggingface.co/leafspark/Pixtral-12B-2409-hf-text-only/

Name	Quant method	Size
Pixtral-12B-2409-hf-text-only.Q2_K.gguf	Q2_K	4.46GB
Pixtral-12B-2409-hf-text-only.IQ3_XS.gguf	IQ3_XS	4.94GB
Pixtral-12B-2409-hf-text-only.IQ3_S.gguf	IQ3_S	5.18GB
Pixtral-12B-2409-hf-text-only.Q3_K_S.gguf	Q3_K_S	5.15GB
Pixtral-12B-2409-hf-text-only.IQ3_M.gguf	IQ3_M	5.33GB
Pixtral-12B-2409-hf-text-only.Q3_K.gguf	Q3_K	5.67GB
Pixtral-12B-2409-hf-text-only.Q3_K_M.gguf	Q3_K_M	5.67GB
Pixtral-12B-2409-hf-text-only.Q3_K_L.gguf	Q3_K_L	6.11GB
Pixtral-12B-2409-hf-text-only.IQ4_XS.gguf	IQ4_XS	6.33GB
Pixtral-12B-2409-hf-text-only.Q4_0.gguf	Q4_0	6.59GB
Pixtral-12B-2409-hf-text-only.IQ4_NL.gguf	IQ4_NL	6.65GB
Pixtral-12B-2409-hf-text-only.Q4_K_S.gguf	Q4_K_S	6.63GB
Pixtral-12B-2409-hf-text-only.Q4_K.gguf	Q4_K	6.96GB
Pixtral-12B-2409-hf-text-only.Q4_K_M.gguf	Q4_K_M	6.96GB
Pixtral-12B-2409-hf-text-only.Q4_1.gguf	Q4_1	7.26GB
Pixtral-12B-2409-hf-text-only.Q5_0.gguf	Q5_0	7.93GB
Pixtral-12B-2409-hf-text-only.Q5_K_S.gguf	Q5_K_S	7.93GB
Pixtral-12B-2409-hf-text-only.Q5_K.gguf	Q5_K	8.13GB
Pixtral-12B-2409-hf-text-only.Q5_K_M.gguf	Q5_K_M	8.13GB
Pixtral-12B-2409-hf-text-only.Q5_1.gguf	Q5_1	8.61GB
Pixtral-12B-2409-hf-text-only.Q6_K.gguf	Q6_K	9.37GB
Pixtral-12B-2409-hf-text-only.Q8_0.gguf	Q8_0	12.13GB

Original model description:

license: apache-2.0 language: - en - fr - de - es - it - pt - ru - zh - ja base_model: - mistral-community/pixtral-12b-240910 tags: - mistral - vision pipeline_tag: text-generation library_name: transformers

Pixtral-12B-2409-hf

This is a HuggingFace transformers conversion of mistral-community/pixtral-12b-240910.

It should work in Transformers, however there are no vision capabilities at the moment.