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 MOSS-Transcribe-Diarize
AMD 4750U GPU3.1×
AMD 4750U CPU1.6×
Q8_0 size0.92 GB
frontier · AMD 4750U GPU0 of 2

verdict: Never first, and outside the leader's 95% CI in all 2 languages. Faster than realtime on the AMD 4750U GPU (3.1×) and AMD 4750U CPU (1.6×).

license: Apache-2.0 · card languages: 2 · timestamps (segment)

standing by language · 2 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.

MOSS-Transcribe-Diarize error best other model error tie: the 95% CIs overlap

quantization · 2 usable languages at Q5_K_M

Q5_K_M is within noise on every one of 2 usable languages: 71% of the Q8_0 file for no measurable accuracy cost.

Q5_K_M file71% of Q8_00.65 GB against 0.92 GB
median error change+1.4%over 2 usable languages
measurably worse0 of 2above the Q8_0 95% confidence interval
worst usable languageEnglish5.13 → 5.30 (+0.17 pts)
measurably worse than Q8_0: above its 95% confidence interval within noise typical noise of one measurement
per-language numbers (2)
English 5.134.57–5.78 5.30+0.17 +3.3%
Mandarin Chinese (CER) 9.238.20–10.17 9.19−0.04 −0.4%

speed · all 73 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-1.7Bahead of it in 2 of 2 shared languagesBreeze-ASR-25closest coverage, 2 languages in common