← Back to community benchmarks

Youssofal--Qwen3.6-27B-MTPLX-Optimized-Speed-fp16meta

M1 Max (24c) · 64 GB · 4bit · 2026-05-19
User comment200k ctx tokens for 5tok/sec
Performance
4k
tokens
97.4
PP tok/s
15.3
TG tok/s
42068
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.9rc1
macOS macOS 26.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 94.3 15.3 15.8 GB view
4k 97.4 15.3 17.3 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 15.3 1.00×
2× 17.4 1.14×
4× 19.7 1.29×