← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · 8bit · 2026-04-23
User commentqwen thinking parameter preset MLX
Performance
4k
tokens
3,679
PP tok/s
96.7
TG tok/s
1113
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.7
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,201 99.8 35.4 GB view
4k 3,679 96.7 36.2 GB current
Batching Results
Batch Size TG tok/s Speedup
99.8 1.00×
162.3 1.63×
239.7 2.40×