← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (24c) · 32 GB · 4bit · 2026-05-18
Performance
32k
tokens
338.8
PP tok/s
19.1
TG tok/s
96712
TTFT (ms)
16.0
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 32,768