← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (24c) · 32 GB · 4bit · 2026-05-07
Performance
8k
tokens
376.8
PP tok/s
42.5
TG tok/s
21739
TTFT (ms)
15.1
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 194.5 46.0 14.7 GB view
8k 376.8 42.5 15.1 GB current
16k 368.3 34.3 15.2 GB view
32k 343.0 19.0 16.0 GB view
64k 298.4 12.1 17.7 GB view