← Back to community benchmarks

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

M1 Ultra (64c) · 128 GB · 8bit · 2026-05-07
Performance
4k
tokens
277.3
PP tok/s
27.3
TG tok/s
14771
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip M1 Ultra (64c)
Memory 128 GB
GPU Cores 64
Software
oMLX v0.3.9.dev1
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 254.9 26.9 28.8 GB view
4k 277.3 27.3 30.3 GB current
Batching Results
Batch Size TG tok/s Speedup
26.9 1.00×
34.1 1.27×
41.3 1.54×