← Back to community benchmarks

Qwen3.6-27B-oQ8-fp16-mtp

M1 Max · 64 GB · 8bit · 2026-05-11
Performance
1k
tokens
142.6
PP tok/s
14.7
TG tok/s
7181
TTFT (ms)
28.8
Peak mem (GB)
Hardware
Chip M1 Max
Memory 64 GB
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 1,024