← Back to community benchmarks

Qwen3.6-35B-A3B-TurboQuant

M3 Max (40c) · 64 GB · 4bit · 2026-05-20
Performance
1k
tokens
1,068
PP tok/s
87.5
TG tok/s
959
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9rc1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,068 87.5 19.2 GB current
4k 1,434 89.1 20.0 GB view
Batching Results
Batch Size TG tok/s Speedup
87.5 1.00×
151.3 1.73×
222.6 2.54×