← Back to community benchmarks

gemma-4-26B-A4B-it-TurboQuant

M1 Max (32c) · 64 GB · 8bit · 2026-04-30
Performance
8k
tokens
398.4
PP tok/s
39.7
TG tok/s
20561
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 411.3 42.2 25.8 GB view
4k 357.0 40.7 26.4 GB view
8k 398.4 39.7 26.6 GB current
16k 338.2 34.2 27.1 GB view
32k 330.8 27.9 28.0 GB view
64k 290.5 19.5 29.2 GB view
Batching Results
Batch Size TG tok/s Speedup
42.2 1.00×
58.2 1.38×
61.9 1.47×
62.3 1.48×