← Back to community benchmarks

diffusiongemma-26B-A4B-it

M5 Max (32c) · 36 GB · 4bit · 2026-07-24
Performance
16k
tokens
2,931
PP tok/s
43.0
TG tok/s
8726
TTFT (ms)
18.1
Peak mem (GB)
Hardware
Chip M5 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.5.3
macOS macOS 26.5.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,855 78.4 16.3 GB view
4k 3,577 31.3 17.1 GB view
16k 2,931 43.0 18.1 GB current
64k 1,910 16.5 22.0 GB view