← Back to community benchmarks

Qwen3.6-35B-A3B

M5 (10c) · 32 GB · 4bit · 2026-07-20
Performance
16k
tokens
1,033
PP tok/s
42.4
TG tok/s
15862
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,064 55.5 19.2 GB view
4k 1,257 55.6 19.9 GB view
8k 1,195 53.2 20.3 GB view
16k 1,033 42.4 21.0 GB current
32k 747.1 37.7 22.3 GB view
64k 458.9 24.4 22.9 GB view