← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Pro (16c) · 48 GB · 4bit · 2026-04-19
Performance
64k
tokens
433.3
PP tok/s
26.6
TG tok/s
151245
TTFT (ms)
25.0
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.6
macOS macOS 26.3.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 644.0 82.4 19.3 GB view
4k 732.3 77.4 20.0 GB view
16k 662.0 41.9 21.0 GB view
64k 433.3 26.6 25.0 GB current
128k 287.0 17.5 30.4 GB view
Batching Results
Batch Size TG tok/s Speedup
82.4 1.00×
118.4 1.44×
138.1 1.68×