resilientai-team-mcte-mistral-voxtral-realtime-gptq-marlin

Home/Models/JaynadTodkarAmol/resilientai-team-mcte-mistral-voxtral-realtime-gptq-marlin

JaynadTodkarAmol/resilientai-team-mcte-mistral-voxtral-realtime-gptq-marlin

kind: fp8
quant: fp8 (8-bit)
family: mistral
modality: automatic-speech-recognition
root model: mistralai/Voxtral-Mini-4B-Realtime-2602
provider: JaynadTodkarAmol
license: apache-2.0
language: —
context: —
library: vllm
vRAM (GB): —
size on disk: —
downloads: 18,389
likes: 0
created: —
last modified: 2026-07-27T18:34:53+00:00 (2026)
huggingface: https://huggingface.co/JaynadTodkarAmol/resilientai-team-mcte-mistral-voxtral-realtime-gptq-marlin
tags: vllmsafetensorsvoxtral_realtimeaudio-to-textvoxtralgptqmarlinfp8automatic-speech-recognitionbase_model:mistralai/Voxtral-Mini-4B-Realtime-2602base_model:quantized:mistralai/Voxtral-Mini-4B-Realtime-2602license:apache-2.04-bitregion:us

benchmark	category	score	context	conf	evidence
DROP	reasoning	25.0	GPTQ, layer 13	medium	`\| GPTQ, drop layer 13 \| 25 \| 0.11583 \| 56.623 \| 2.1464 \| 26,427 \|`
DROP	reasoning	24.0	GPTQ, layers 12-13	medium	`\| GPTQ, drop layers 12-13 \| 24 \| 0.11390 \| 54.604 \| 2.0573 \| 26,429 \|`
DROP	reasoning	23.0	GPTQ, layers 12-14	medium	`\| GPTQ, drop layers 12-14 \| 23 \| 0.12162 \| 54.515 \| 2.0369 \| 26,435 \|`
DROP	reasoning	22.0	GPTQ, layers 11-14	medium	`\| GPTQ, drop layers 11-14 \| 22 \| 0.13320 \| 53.795 \| 2.0443 \| 26,375 \|`
WER LibriSpeech	speech-asr	10.0	LibriSpeech (`openslr/librispeech_asr`)	medium	\| LibriSpeech (`openslr/librispeech_asr`) \| English \| `test-clean` \| 10 \|
WER FLEURS	speech-asr	10.0	FLEURS (`google/fleurs`)	medium	\| FLEURS (`google/fleurs`) \| Hindi (`hi_in`) \| `test` \| 10 \|

none scraped.