← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 128 GB · 8bit · 2026-06-04
Performance
16k
tokens
1,220
PP tok/s
57.0
TG tok/s
13431
TTFT (ms)
28.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.2.dev2
macOS macOS 15.7.7
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 1,220 57.0 28.8 GB current
64k 806.7 35.9 39.3 GB view