← Back to community benchmarks

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

M4 Max (40c) · 64 GB · 8bit · 2026-06-04
Performance
16k
tokens
1,056
PP tok/s
61.6
TG tok/s
15520
TTFT (ms)
28.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.4.1
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,200 70.8 25.8 GB view
4k 1,390 68.2 26.2 GB view
8k 1,245 64.9 27.1 GB view
16k 1,056 61.6 28.8 GB current
32k 926.2 50.8 32.3 GB view
64k 745.8 22.7 39.3 GB view