mattbucci
/

Devstral-24B-AWQ

4-bit precision

Model card Files Files and versions

Devstral-24B-AWQ / config.json

Commit History

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

91382f5
verified

mattbucci commited on 9 days ago

Devstral 24B AWQ: GPTQ-calibrated, BOS-fixed chat template, 37 tok/s on RDNA4

df87209
verified

mattbucci commited on 23 days ago