← Back to community benchmarks

Qwen3.6-35B-A3B

M2 Max (30c) · 64 GB · 4bit · 2026-04-16
Performance
1k
tokens
527.3
PP tok/s
79.3
TG tok/s
1942
TTFT (ms)
19.3
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 64 GB
GPU Cores 30
Software
oMLX v0.3.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 527.3 79.3 19.3 GB current
4k 618.1 78.6 20.0 GB view
32k 537.8 49.0 22.4 GB view
64k 450.2 29.7 25.0 GB view
Batching Results
Batch Size TG tok/s Speedup
79.3 1.00×
107.4 1.35×
127.0 1.60×