← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Pro (20c) · 48 GB · 4bit · 2026-07-23
Performance
16k
tokens
839.6
PP tok/s
71.0
TG tok/s
19514
TTFT (ms)
20.6
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.5.3
macOS macOS 27.0
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 921.4 84.3 19.4 GB view
4k 976.2 81.0 20.1 GB view
8k 933.0 76.9 20.3 GB view
16k 839.6 71.0 20.6 GB current
32k 699.1 61.9 21.3 GB view
64k 524.0 48.4 22.5 GB view
128k 348.9 35.0 25.1 GB view
195k 257.6 26.5 28.4 GB view
Batching Results
Batch Size TG tok/s Speedup
84.3 1.00×
134.7 1.60×
174.0 2.06×
215.7 2.56×