← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 64 GB · 4bit · 2026-06-02
Performance
32k
tokens
1,147
PP tok/s
67.0
TG tok/s
28580
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.4.0rc1
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 1,279 80.0 15.2 GB view
32k 1,147 67.0 16.5 GB current
64k 935.6 51.1 18.5 GB view