← Back to community benchmarks

Ternary-Bonsai-27B

M1 Max (32c) · 32 GB · 2bit · 2026-07-21
Performance
16k
tokens
148.6
PP tok/s
22.3
TG tok/s
110243
TTFT (ms)
11.5
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.5.2rc2
macOS macOS 27.0
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 154.9 23.7 10.2 GB view
16k 148.6 22.3 11.5 GB current
64k 114.7 12.5 15.4 GB view