← Back to community benchmarks

Qwen3.6-35B-A3B

M4 (10c) · 32 GB · 4bit · 2026-04-28
Performance
1k
tokens
376.8
PP tok/s
47.0
TG tok/s
2718
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.5.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 376.8 47.0 19.2 GB current
4k 392.1 44.6 19.9 GB view
8k 386.7 41.1 20.2 GB view
Batching Results
Batch Size TG tok/s Speedup
47.0 1.00×
70.4 1.50×
80.9 1.72×