← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 64 GB · 8bit · 2026-07-22
Performance
16k
tokens
1,188
PP tok/s
64.7
TG tok/s
13794
TTFT (ms)
27.0
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 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 1,452 71.0 26.2 GB view
16k 1,188 64.7 27.0 GB current
64k 804.9 45.1 29.7 GB view