← Back to community benchmarks

Gemma-4-26B-A4B-Heretic

M4 Max (32c) · 36 GB · 4bit · 2026-06-03
Performance
64k
tokens
794.8
PP tok/s
49.6
TG tok/s
82453
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.12
macOS macOS 26.5
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 971.8 64.8 15.3 GB view
64k 794.8 49.6 17.7 GB current