← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 128 GB · 4bit · 2026-04-30
Performance
195k
tokens
426.4
PP tok/s
23.1
TG tok/s
469029
TTFT (ms)
36.1
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 15.7.3
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,261 115.2 19.3 GB view
4k 1,677 111.1 20.0 GB view
195k 426.4 23.1 36.1 GB current
Batching Results
Batch Size TG tok/s Speedup
115.2 1.00×
186.3 1.62×
259.5 2.25×
527.1 4.58×