← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Max (40c) · 64 GB · 8bit · 2026-05-02
Performance
16k
tokens
1,356
PP tok/s
64.8
TG tok/s
12080
TTFT (ms)
37.4
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,015 73.8 35.4 GB view
4k 1,444 71.5 36.2 GB view
8k 1,444 68.8 36.5 GB view
16k 1,356 64.8 37.4 GB current
Batching Results
Batch Size TG tok/s Speedup
73.8 1.00×
115.9 1.57×
171.8 2.33×