← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Ultra (80c) · 512 GB · 4bit · 2026-04-16
Performance
1k
tokens
1,688
PP tok/s
98.7
TG tok/s
607
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.4
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,688 98.7 19.2 GB current
8k 2,671 88.7 20.4 GB view
32k 2,203 69.2 22.4 GB view
64k 1,662 52.8 25.0 GB view
128k 1,036 35.3 30.4 GB view
Batching Results
Batch Size TG tok/s Speedup
98.7 1.00×
172.6 1.75×
351.2 3.56×
678.2 6.87×