← Back to community benchmarks

Qwen3.5-35B-A3B

M5 Pro (20c) · 64 GB · 8bit · 2026-03-14
Performance
1k
tokens
1,741
PP tok/s
67.0
TG tok/s
588
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.11
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,741 67.0 36.2 GB current
4k 1,846 64.7 36.3 GB view
8k 1,945 61.0 36.5 GB view
16k 1,796 56.4 37.0 GB view
32k 1,588 48.3 37.8 GB view
64k 1,192 36.7 39.5 GB view
128k 786.2 19.9 42.8 GB view
195k 574.1 8.4 46.4 GB view
Batching Results
Batch Size TG tok/s Speedup
67.0 1.00×
104.6 1.56×
144.5 2.16×
186.3 2.78×