← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · 8bit · 2026-04-30
Performance
64k
tokens
2,156
PP tok/s
48.6
TG tok/s
30393
TTFT (ms)
41.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,046 97.4 35.4 GB view
4k 3,654 95.7 36.2 GB view
32k 3,110 72.2 38.5 GB view
64k 2,156 48.6 41.2 GB current
Batching Results
Batch Size TG tok/s Speedup
97.4 1.00×
161.7 1.66×
246.8 2.53×