← Back to community benchmarks

Qwen3.5-35B-A3B

M5 Pro (20c) · 64 GB · 8bit · 2026-03-28
Performance
16k
tokens
2,049
PP tok/s
48.2
TG tok/s
7995
TTFT (ms)
38.2
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.21
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 2,208 51.1 37.5 GB view
16k 2,049 48.2 38.2 GB current
32k 1,735 39.7 39.5 GB view
64k 1,251 30.6 42.1 GB view