← Back to community benchmarks

gpt-oss-120b-MXFP4-Q8

M5 Max (40c) · 128 GB · 4bit · 2026-03-13
Performance
16k
tokens
622.3
PP tok/s
38.4
TG tok/s
26329
TTFT (ms)
59.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.10
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 497.6 85.1 59.2 GB view
4k 619.3 77.3 59.3 GB view
8k 639.2 63.5 59.5 GB view
16k 622.3 38.4 59.8 GB current
64k 514.0 16.3 61.6 GB view
Batching Results
Batch Size TG tok/s Speedup
85.1 1.00×
118.2 1.39×
145.2 1.71×
157.2 1.85×