← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 128 GB · 8bit · 2026-06-07
Performance
64k
tokens
490.1
PP tok/s
15.4
TG tok/s
133722
TTFT (ms)
41.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.2rc1
macOS macOS 26.5.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 694.4 29.5 35.4 GB view
4k 886.0 21.7 36.2 GB view
16k 820.7 27.3 37.1 GB view
64k 490.1 15.4 41.2 GB current
Batching Results
Batch Size TG tok/s Speedup
29.5 1.00×
31.6 1.07×
39.3 1.33×
92.1 3.12×