← Back to community benchmarks

gemma-4-26B-A4B-it-uncensored-heretic-ara8bit-int8-affine

M1 Max (32c) · 64 GB · 8bit · 2026-05-22
Performance
32k
tokens
444.9
PP tok/s
30.3
TG tok/s
73655
TTFT (ms)
29.4
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9
macOS macOS 26.2
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 478.9 36.8 28.1 GB view
32k 444.9 30.3 29.4 GB current
64k 388.4 20.4 31.4 GB view