← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 (10c) · 32 GB · 4bit · 2026-04-26
Performance
1k
tokens
349.3
PP tok/s
33.6
TG tok/s
2932
TTFT (ms)
11.7
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 349.3 33.6 11.7 GB current
4k 383.3 32.4 11.8 GB view
Batching Results
Batch Size TG tok/s Speedup
33.6 1.00×
47.6 1.42×
53.6 1.60×