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.
modelgigaam-v3-e2e-rnnt
AMD 4750U GPU15.0×
AMD 4750U CPU7.9×
Q8_0 size0.25 GB
frontier · AMD 4750U GPU1 of 1
verdict: Tied with the leader in its one benchmarked language, Russian (overlapping 95% CIs). Faster than realtime on the AMD 4750U GPU (15.0×) and AMD 4750U CPU (7.9×).
license: MIT · card languages: 1 · timestamps (token)
standing by language · 1 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.
gigaam-v3-e2e-rnnt 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: 325% of the Q8_0 file for no measurable accuracy cost. F16 is within noise on the one usable language: 165% 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: 75% of the Q8_0 file for no measurable accuracy cost. Q4_K_M is within noise on the one usable language: 67% of the Q8_0 file for no measurable accuracy cost.
F32 file325% of Q8_00.83 GB against 0.25 GB
median error change+0.0%over 1 usable language
measurably worse0 of 1above the Q8_0 95% confidence interval