Voxtral Small 24B 2507 GGUF
This is a static quant of mistralai/Voxtral-Small-24B-2507, made with llama.cpp commit 00fa15fedc79263fa0285e6a3bbb0cfb3e3878a2.
Modellquelle
- Art
- Other
- Dateigröße
- 1,29–23,3 GB
- Basismodell
- mistralai/Voxtral-Small-24B-2507
- Version
- vGgml model Q4 K S
- Aktualisiert
- 23. Okt. 2026
- Quelle
- Hugging Face
Quellenbeschreibung
This is a static quant of mistralai/Voxtral-Small-24B-2507, made with llama.cpp commit 00fa15fedc79263fa0285e6a3bbb0cfb3e3878a2.
Due to limited storage space on my computer, the q4_K_M quant is requantized from the q8_0 instead of the full precision model, wich might not be ideal for the best quality.
(the audio mmproj also works with other existing based on Mistral Small 3.2. I tried it, and it worked surprisingly well)
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 7. Aug.
Modellartefakte
3 Artefakte
Modellartefakte
3 ArtefakteQuellenauszüge
2 Auszüge
Quellenauszüge
2 Auszüge--- license: apache-2.0 base_model: - mistralai/Voxtral-Small-24B-2507 pipeline_tag: audio-text-to-text --- This is a static quant of mistralai/Voxtral-Small-24B-2507, made with llama.cpp commit 00fa15fedc79263fa0285e6a3bbb0cfb3e3878a2. Due to limited storage space on my computer, the q4_K_M quant is requantized from the q8_0 instead of the full precision model, wich might not be ideal for the best quality. (the audio mmproj also works with other existing based on Mistral Small 3.2. I tried it, and it worked surprisingly well)
Source context: 81 downloads · 3 likes · Pipeline audio-text-to-text · Repo stduhpf/Voxtral-Small-24B-2507-GGUF
