← Back to community benchmarks

Qwen3.6-35B-A3B

M5 (10c) · 32 GB · 4bit · 2026-07-20
Performance
4k
tokens
1,273
PP tok/s
55.3
TG tok/s
3218
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,080 57.7 19.2 GB view
4k 1,273 55.3 19.9 GB current
8k 1,191 52.5 20.4 GB view
16k 1,034 47.4 21.1 GB view
32k 762.6 37.6 22.4 GB view
64k 502.4 25.7 23.2 GB view