← Back to community benchmarks

gemma-4-26B-A4B-it-heretic-oQ8

M1 Max (24c) · 64 GB · 8bit · 2026-05-23
Performance
16k
tokens
583.5
PP tok/s
31.7
TG tok/s
28081
TTFT (ms)
27.1
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.9
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 532.0 36.0 25.8 GB view
4k 610.6 34.0 26.4 GB view
8k 617.2 33.5 26.6 GB view
16k 583.5 31.7 27.1 GB current
32k 528.6 28.8 28.0 GB view
64k 437.9 24.4 30.0 GB view