← Back to community benchmarks

gemma-4-26B-A4B-it

M1 Max (24c) · 32 GB · 4bit · 2026-05-30
Performance
16k
tokens
360.7
PP tok/s
37.1
TG tok/s
45419
TTFT (ms)
15.2
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 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 360.7 37.1 15.2 GB current
32k 333.1 30.4 16.4 GB view
64k 289.6 18.2 17.5 GB view