HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Qwen3-ASR-1.7B-fp8

vrfai/Qwen3-ASR-1.7B-fp8

kind
fp8
quant
fp8 (8-bit)
family
qwen
modality
automatic-speech-recognition
root model
Qwen/Qwen3-ASR-1.7B
provider
vrfai
license
apache-2.0
language
en, zh, fr, de, ja, ko, vi, ar, es, it, pt, ru
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
401
likes
5
created
—
last modified
2026-06-06T08:45:58+00:00 (2026)
huggingface
https://huggingface.co/vrfai/Qwen3-ASR-1.7B-fp8
tags
safetensorsqwen3_asrasrspeechquantizationfp8nvidia-modeloptvllmautomatic-speech-recognitionenzhfrdejakoviaresitptruthnlpl

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr7.6high| FP8 | 7.60% |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.