← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M3 Max (40c) · 48 GB · 4bit · 2026-03-11
Performance
1k
tokens
849.9
PP tok/s
89.7
TG tok/s
1205
TTFT (ms)
11.4
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.2.8
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 849.9 89.7 11.4 GB current
4k 932.8 82.7 11.5 GB view
Batching Results
Batch Size TG tok/s Speedup
89.7 1.00×
124.6 1.39×
157.9 1.76×