← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Pro (20c) · 64 GB · 8bit · 2026-04-29
Performance
4k
tokens
2,095
PP tok/s
63.6
TG tok/s
1955
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8rc1
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,383 65.0 35.4 GB view
4k 2,095 63.6 36.2 GB current
8k 2,112 61.7 36.5 GB view
16k 2,032 56.9 37.1 GB view
32k 1,747 46.3 38.5 GB view
64k 1,285 36.5 41.2 GB view
128k 816.0 24.9 46.5 GB view
Batching Results
Batch Size TG tok/s Speedup
65.0 1.00×
101.6 1.56×
140.2 2.16×
183.8 2.83×