← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 64 GB · 8bit · 2026-07-22
Performance
4k
tokens
1,452
PP tok/s
71.0
TG tok/s
2821
TTFT (ms)
26.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 26.5.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 1,452 71.0 26.2 GB current
16k 1,188 64.7 27.0 GB view
64k 804.9 45.1 29.7 GB view