← Back to community benchmarks

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

M1 Max (32c) · 64 GB · 8bit · 2026-05-22
Performance
16k
tokens
478.9
PP tok/s
36.8
TG tok/s
34213
TTFT (ms)
28.1
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9
macOS macOS 26.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 478.9 36.8 28.1 GB current
32k 444.9 30.3 29.4 GB view
64k 388.4 20.4 31.4 GB view