← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 (10c) · 32 GB · 4bit · 2026-03-10
Performance
4k
tokens
318.0
PP tok/s
32.1
TG tok/s
12880
TTFT (ms)
11.5
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 15.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 292.3 34.5 11.4 GB view
4k 318.0 32.1 11.5 GB current
Batching Results
Batch Size TG tok/s Speedup
34.5 1.00×
46.7 1.35×
53.9 1.56×
55.1 1.60×