← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 128 GB · 4bit · 2026-05-19
Performance
64k
tokens
1,017
PP tok/s
60.4
TG tok/s
64457
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4
Context 65,536