← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M5 (10c) · 32 GB · 4bit · 2026-05-18
Performance
1k
tokens
709.8
PP tok/s
35.0
TG tok/s
1443
TTFT (ms)
11.7
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 709.8 35.0 11.7 GB current
4k 965.6 33.8 11.8 GB view
Batching Results
Batch Size TG tok/s Speedup
35.0 1.00×
49.5 1.41×
58.0 1.66×