← Back to community benchmarks

gemma-4-26B-A4B-it

M1 Max (24c) · 32 GB · 4bit · 2026-05-30
Performance
32k
tokens
333.1
PP tok/s
30.4
TG tok/s
98383
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.3.12
macOS macOS 15.7.7
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 360.7 37.1 15.2 GB view
32k 333.1 30.4 16.4 GB current
64k 289.6 18.2 17.5 GB view