model detail

Where this model stands against the best model in each language at Q8_0, its speed on an AMD Ryzen 4750U laptop, and what the card says. Add a second model to compare them head to head.

model Qwen3-ASR-1.7B
AMD 4750U GPU3.8×
AMD 4750U CPU2.0×
Q8_0 size2.04 GB
frontier · AMD 4750U GPU14 of 30

verdict: Best in 10 of 30 languages, and tied with the leader in 4 more (overlapping 95% CIs). Weakest relative to the field in Finnish (3.3× the leader's error), Greek (3.3×), and Romanian (3.0×). Faster than realtime on the AMD 4750U GPU (3.8×) and AMD 4750U CPU (2.0×).

license: Apache-2.0 · card languages: 30 · lang detect

standing by language · 30 benchmarked

Each bar compares this model with the best other model in that language, on a log scale: left of center it is ahead, right of center behind, and the other model is named on the row. The two error rates use the legend colors: this model first, the other model second. Faded bars are ties, where the 95% confidence intervals overlap. Sorted strongest standing first. Hover a row for full details.

Qwen3-ASR-1.7B error best other model error tie: the 95% CIs overlap

speed · all 19 models on the AMD 4750U GPU

× realtime, log scale. Left of the realtime marker, transcribing takes longer than the recording. Hover a dot for the model.

compare with

Qwen3-ASR-0.6Bsame familywhisper-large-v3ahead of it in 19 of 30 shared languageswhisper-large-v3-turboclosest coverage, 30 languages in common