← Back to community benchmarks

OmniCoder-9B

M4 Max (40c) · 48 GB · 8bit · 2026-03-13
Performance
16k
tokens
460.3
PP tok/s
24.4
TG tok/s
35593
TTFT (ms)
10.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.2.10
macOS macOS 26.3
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 536.6 35.7 9.9 GB view
4k 437.5 33.8 10.1 GB view
8k 457.0 33.3 10.3 GB view
16k 460.3 24.4 10.8 GB current
32k 469.8 24.0 11.9 GB view
64k 413.8 15.5 13.9 GB view
Batching Results
Batch Size TG tok/s Speedup
35.7 1.00×
74.9 2.10×
93.7 2.62×