← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Pro (16c) · 48 GB · 4bit · 2026-05-18
Performance
16k
tokens
679.0
PP tok/s
54.5
TG tok/s
24128
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.5.dev1
macOS macOS 15.7.3
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 662.9 83.6 19.3 GB view
4k 750.0 78.5 20.0 GB view
8k 732.1 70.4 20.4 GB view
16k 679.0 54.5 21.0 GB current
Batching Results
Batch Size TG tok/s Speedup
83.6 1.00×
118.8 1.42×
141.9 1.70×
166.0 1.99×