← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · 8bit · 2026-07-19
Performance
64k
tokens
2,242
PP tok/s
68.5
TG tok/s
29233
TTFT (ms)
42.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.1
macOS macOS 27.0
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,237 89.0 35.4 GB view
4k 4,216 88.3 36.2 GB view
8k 4,034 85.8 36.6 GB view
16k 3,722 84.1 37.5 GB view
32k 3,217 75.2 39.3 GB view
64k 2,242 68.5 42.0 GB current
128k 1,398 57.9 48.0 GB view
195k 984.9 45.2 54.9 GB view
Batching Results
Batch Size TG tok/s Speedup
89.0 1.00×
156.7 1.76×
248.2 2.79×
321.7 3.61×