← Back to community benchmarks
gpt-oss-20b-MXFP4-Q8
Performance
32k
tokens
261.8
PP tok/s
5.3
TG tok/s
125173
TTFT (ms)
12.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
32,768