← Back to community benchmarks

gemma-4-26b-a4b-it

M4 (10c) · 32 GB · 4bit · 2026-05-06
Performance
8k
tokens
368.8
PP tok/s
30.6
TG tok/s
22212
TTFT (ms)
15.0
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 376.3 32.2 14.9 GB view
8k 368.8 30.6 15.0 GB current
16k 347.7 28.5 15.5 GB view
64k 246.7 17.1 18.5 GB view