← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Pro (20c) · 64 GB · 8bit · 2026-04-20
Performance
1k
tokens
1,414
PP tok/s
67.3
TG tok/s
724
TTFT (ms)
35.4
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
1× 67.3 1.00×
2× 102.8 1.53×
4× 135.7 2.02×
8× 175.2 2.60×