← Back to community benchmarks

gpt-oss-120b-MXFP4-Q8

M5 Max (40c) · 128 GB · 4bit · 2026-04-04
Performance
32k
tokens
1,368
PP tok/s
39.0
TG tok/s
23958
TTFT (ms)
60.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.2
macOS macOS 26.4
Context 32,768