← Back to community benchmarks

Ternary-Bonsai-27B

M5 Pro (20c) · 64 GB · 2bit · 2026-07-23
Performance
1k
tokens
482.2
PP tok/s
30.7
TG tok/s
2124
TTFT (ms)
8.9
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.5.3
macOS macOS 26.5.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 482.2 30.7 8.9 GB current
32k 142.0 23.4 14.7 GB view
64k 130.2 18.9 19.7 GB view