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.
modelparakeet-primeline
AMD 4750U GPU25.0×
AMD 4750U CPU13.6×
Q8_0 size0.69 GB
frontier · AMD 4750U GPU0 of 25
verdict: Never first, and outside the leader's 95% CI in all 25 languages. Weakest relative to the field in Slovenian (4.0× the leader's error), Greek (3.9×), and Latvian (2.8×). Faster than realtime on the AMD 4750U GPU (25.0×) and AMD 4750U CPU (13.6×).
license: CC-BY-4.0 · card languages: 25 · lang detecttimestamps (token)
standing by language · 25 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.
parakeet-primeline errorbest other model errortie: the 95% CIs overlap
quantization · 1 usable language at F32, F16, Q6_K, Q5_K_M, Q4_K_M
F32 is within noise on the one usable language: 339% of the Q8_0 file for no measurable accuracy cost. F16 is within noise on the one usable language: 170% of the Q8_0 file for no measurable accuracy cost. Q6_K is within noise on the one usable language: 83% of the Q8_0 file for no measurable accuracy cost. Q5_K_M is within noise on the one usable language: 74% of the Q8_0 file for no measurable accuracy cost. Q4_K_M is within noise on the one usable language: 66% of the Q8_0 file for no measurable accuracy cost.
F32 file339% of Q8_02.34 GB against 0.69 GB
median error change+0.3%over 1 usable language
measurably worse0 of 1above the Q8_0 95% confidence interval