← Back to community benchmarks

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

M4 Max (40c) · 128 GB · 4bit · 2026-05-01
Performance
32k
tokens
1,241
PP tok/s
75.9
TG tok/s
26400
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
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
8k 1,417 97.3 14.8 GB view
16k 1,368 89.2 15.6 GB view
32k 1,241 75.9 16.5 GB current
64k 1,030 59.1 17.7 GB view
128k 754.4 40.6 21.2 GB view
195k 577.3 30.3 25.0 GB view