mattbucci
/

Devstral-24B-AWQ

4-bit precision

Model card Files Files and versions

Devstral-24B-AWQ

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

mattbucci's picture

add quantization_config.ignore=['lm_head'] (downstream audit fix)

91382f5 verified 9 days ago

.gitattributes

1.57 kB
Devstral 24B AWQ: GPTQ-calibrated, BOS-fixed chat template, 37 tok/s on RDNA4 23 days ago
README.md

1.72 kB
Vision tested and working 23 days ago
chat_template.jinja

5.32 kB
Devstral 24B AWQ: GPTQ-calibrated, BOS-fixed chat template, 37 tok/s on RDNA4 23 days ago
config.json

1.84 kB
add quantization_config.ignore=['lm_head'] (downstream audit fix) 9 days ago
generation_config.json

153 Bytes
Devstral 24B AWQ: GPTQ-calibrated, BOS-fixed chat template, 37 tok/s on RDNA4 23 days ago
model-vision.safetensors

878 MB
xet

Devstral 24B AWQ: GPTQ-calibrated, BOS-fixed chat template, 37 tok/s on RDNA4 23 days ago
model.safetensors

14.2 GB
xet

Devstral 24B AWQ: GPTQ-calibrated, BOS-fixed chat template, 37 tok/s on RDNA4 23 days ago
model.safetensors.index.json

96.4 kB
Devstral 24B AWQ: GPTQ-calibrated, BOS-fixed chat template, 37 tok/s on RDNA4 23 days ago
processor_config.json

976 Bytes
Devstral 24B AWQ: GPTQ-calibrated, BOS-fixed chat template, 37 tok/s on RDNA4 23 days ago
tokenizer.json

17.1 MB
xet

Devstral 24B AWQ: GPTQ-calibrated, BOS-fixed chat template, 37 tok/s on RDNA4 23 days ago
tokenizer_config.json

21.2 kB
Devstral 24B AWQ: GPTQ-calibrated, BOS-fixed chat template, 37 tok/s on RDNA4 23 days ago