← Back to community benchmarks

gpt-oss-20b

M1 Max (24c) · 32 GB · unknown · 2026-03-16
Performance
1k
tokens
263.1
PP tok/s
47.2
TG tok/s
3891
TTFT (ms)
13.1
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.2.9
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 263.1 47.2 13.1 GB current
4k 302.0 42.8 13.1 GB view
Batching Results
Batch Size TG tok/s Speedup
47.2 1.00×
37.2 0.79×
55.1 1.17×