← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Max (30c) · 36 GB · 4bit · 2026-04-28
Performance
64k
tokens
662.0
PP tok/s
7.0
TG tok/s
98990
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.3.8.dev2
macOS macOS 26.3
Context 65,536