← Back to community benchmarks

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

M4 Max (40c) · 64 GB · 4bit · 2026-06-01
Performance
16k
tokens
1,285
PP tok/s
67.9
TG tok/s
12755
TTFT (ms)
18.1
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.4.0rc1
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 1,285 67.9 18.1 GB current
32k 1,151 58.1 19.4 GB view
64k 925.9 44.1 21.4 GB view