← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 128 GB · 4bit · 2026-05-12
Performance
4k
tokens
1,642
PP tok/s
106.1
TG tok/s
2494
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,133 110.8 19.3 GB view
4k 1,642 106.1 20.0 GB current
8k 1,634 100.7 20.5 GB view
Batching Results
Batch Size TG tok/s Speedup
110.8 1.00×
181.4 1.64×
261.9 2.36×
313.2 2.83×