← Back to community benchmarks

OmniCoder-9B

M5 Max (32c) · 36 GB · 8bit · 2026-03-16
Performance
1k
tokens
1,508
PP tok/s
44.1
TG tok/s
679
TTFT (ms)
9.9
Peak mem (GB)
Hardware
Chip M5 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.2.13
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,508 44.1 9.9 GB current
4k 2,212 43.4 10.1 GB view
8k 2,257 42.3 10.3 GB view
16k 2,096 40.7 10.8 GB view
32k 1,785 35.7 11.9 GB view
64k 1,411 20.7 13.9 GB view
128k 1,068 14.5 18.3 GB view
195k 768.2 6.1 22.8 GB view
Batching Results
Batch Size TG tok/s Speedup
44.1 1.00×
84.5 1.92×