← Back to community benchmarks

rocinante-x-12b

M2 Max (38c) · 96 GB · 8bit · 2026-03-12
Performance
4k
tokens
255.0
PP tok/s
24.0
TG tok/s
16067
TTFT (ms)
13.3
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 96 GB
GPU Cores 38
Software
oMLX v0.2.10
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 258.1 26.8 12.8 GB view
4k 255.0 24.0 13.3 GB current
8k 238.9 21.0 14.0 GB view
Batching Results
Batch Size TG tok/s Speedup
26.8 1.00×
48.6 1.81×
65.8 2.46×
47.4 1.77×