← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Max (40c) · 64 GB · 8bit · 2026-05-02
Performance
32k
tokens
1,017
PP tok/s
47.6
TG tok/s
32230
TTFT (ms)
27.5
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 15.7.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 1,017 47.6 27.5 GB current
64k 783.9 39.0 30.0 GB view
128k 591.5 27.8 34.2 GB view