← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (32c) · 64 GB · 4bit · 2026-04-12
Performance
16k
tokens
483.0
PP tok/s
19.7
TG tok/s
33922
TTFT (ms)
15.4
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.5.dev1
macOS macOS 26.0.1
Context 16,384