← Back to community benchmarks

gemma-4-26B-A4B-it-heretic

M4 Pro (16c) · 24 GB · 4bit · 2026-05-14
Performance
32k
tokens
513.9
PP tok/s
46.1
TG tok/s
63758
TTFT (ms)
16.0
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 513.9 46.1 16.0 GB current
64k 427.2 36.1 17.7 GB view