← Back to community benchmarks

community--Qwen3.6-35B-A3B

M5 Pro (20c) · 64 GB · 8bit · 2026-07-05
Performance
8k
tokens
2,075
PP tok/s
67.4
TG tok/s
3948
TTFT (ms)
36.5
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.4.4
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,371 71.1 35.4 GB view
4k 2,051 69.7 36.2 GB view
8k 2,075 67.4 36.5 GB current
16k 1,940 64.5 37.1 GB view
Batching Results
Batch Size TG tok/s Speedup
71.1 1.00×
101.8 1.43×
138.5 1.95×