← Back to community benchmarks

gpt-oss-20b-RotorQuant

M1 Max (32c) · 64 GB · 4bit · 2026-04-29
Performance
32k
tokens
342.2
PP tok/s
28.1
TG tok/s
95759
TTFT (ms)
12.1
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.8rc1korokke
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 510.3 59.8 11.3 GB view
32k 342.2 28.1 12.1 GB current