← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 64 GB · 4bit · 2026-04-26
Performance
16k
tokens
1,206
PP tok/s
56.0
TG tok/s
13590
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,063 67.4 19.3 GB view
4k 1,120 65.9 20.0 GB view
8k 1,163 60.5 20.4 GB view
16k 1,206 56.0 21.0 GB current
Batching Results
Batch Size TG tok/s Speedup
67.4 1.00×
101.6 1.51×
121.2 1.80×
152.0 2.26×