← Back to community benchmarks

Qwen3.6-35B-A3B

M1 Pro (14c) · 32 GB · 4bit · 2026-04-20
Performance
16k
tokens
262.1
PP tok/s
29.9
TG tok/s
62516
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 32 GB
GPU Cores 14
Software
oMLX v0.3.5
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 247.6 42.7 19.3 GB view
4k 279.0 40.3 20.0 GB view
8k 273.5 35.8 20.4 GB view
16k 262.1 29.9 21.0 GB current
32k 236.0 21.5 22.4 GB view
Batching Results
Batch Size TG tok/s Speedup
42.7 1.00×
50.9 1.19×
57.1 1.34×