← Back to community benchmarks

gpt-oss-120b

M2 Max (38c) · 96 GB · 4bit · 2026-03-08
Performance
1k
tokens
187.7
PP tok/s
54.9
TG tok/s
5457
TTFT (ms)
58.0
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 96 GB
GPU Cores 38
Software
oMLX v0.2.6
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 187.7 54.9 58.0 GB current
4k 182.0 44.7 58.1 GB view
8k 183.9 37.1 58.3 GB view
16k 177.1 22.7 58.6 GB view
32k 165.3 14.6 59.2 GB view
Batching Results
Batch Size TG tok/s Speedup
54.9 1.00×
55.8 1.02×
60.7 1.11×
64.1 1.17×