← Back to community benchmarks

Qwen3.5-35B-A3B

M1 Pro (14c) · 32 GB · 4bit · 2026-03-11
Performance
4k
tokens
264.5
PP tok/s
41.7
TG tok/s
15483
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 32 GB
GPU Cores 14
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 249.2 45.9 20.1 GB view
4k 264.5 41.7 20.2 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 45.9 1.00×
2× 53.7 1.17×
4× 59.8 1.30×