← Back to community benchmarks

gemma-4-26b-a4b-it-oQ8

M4 Pro (20c) · 64 GB · 8bit · 2026-05-06
Performance
8k
tokens
724.6
PP tok/s
42.6
TG tok/s
11305
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 355.6 44.2 26.2 GB view
8k 724.6 42.6 26.6 GB current
16k 648.5 39.8 26.7 GB view
32k 560.0 34.9 27.5 GB view
64k 476.7 26.4 29.2 GB view
128k 356.2 17.1 32.7 GB view