← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M1 Max (32c) · 64 GB · 4bit · 2026-03-18
Performance
1k
tokens
428.5
PP tok/s
62.5
TG tok/s
2390
TTFT (ms)
11.7
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.2.19
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 428.5 62.5 11.7 GB current
4k 476.6 57.3 11.8 GB view
Batching Results
Batch Size TG tok/s Speedup
62.5 1.00×
71.1 1.14×
69.0 1.10×