← Back to community benchmarks

gemma-4-26B-A4B-it-OptiQ

M4 Max (40c) · 64 GB · 4bit · 2026-05-27
Performance
16k
tokens
1,275
PP tok/s
71.7
TG tok/s
12853
TTFT (ms)
18.1
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.11
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 1,275 71.7 18.1 GB current
32k 1,154 59.0 19.4 GB view
64k 937.9 48.2 21.4 GB view