← Back to community benchmarks

community--gpt-oss-20b-MXFP4-Q4

M2 Max (30c) · 32 GB · 4bit · 2026-06-13
Performance
1k
tokens
410.7
PP tok/s
89.3
TG tok/s
2493
TTFT (ms)
10.9
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 32 GB
GPU Cores 30
Software
oMLX v0.4.4rc1
macOS macOS 26.5.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 410.7 89.3 10.9 GB current
4k 497.1 81.8 11.0 GB view
Batching Results
Batch Size TG tok/s Speedup
89.3 1.00×
94.8 1.06×
105.4 1.18×