← Back to community benchmarks

Qwen3.5-35B-A3B

M2 Pro (16c) · 32 GB · 4bit · 2026-03-11
Performance
4k
tokens
187.5
PP tok/s
20.3
TG tok/s
21840
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.2.6
macOS macOS 15.7.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 225.6 23.9 20.1 GB view
4k 187.5 20.3 20.2 GB current
8k 192.7 27.1 20.4 GB view
16k 174.4 19.8 20.8 GB view
Batching Results
Batch Size TG tok/s Speedup
23.9 1.00×
32.1 1.34×
38.0 1.59×
45.4 1.90×