← Back to community benchmarks

Qwen3.6-35B-A3B-TurboQuant

M4 (10c) · 24 GB · 2bit · 2026-05-04
Performance
8k
tokens
446.4
PP tok/s
56.9
TG tok/s
18350
TTFT (ms)
12.3
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 427.2 69.0 11.1 GB view
4k 461.7 64.1 11.9 GB view
8k 446.4 56.9 12.3 GB current
16k 408.9 49.1 13.1 GB view
32k 338.5 37.1 14.6 GB view
Batching Results
Batch Size TG tok/s Speedup
69.0 1.00×
83.7 1.21×
84.8 1.23×