← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Pro (20c) · 48 GB · 4bit · 2026-03-10
Performance
4k
tokens
868.6
PP tok/s
72.3
TG tok/s
4716
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 753.6 61.8 20.1 GB view
4k 868.6 72.3 20.2 GB current
8k 773.1 64.2 20.4 GB view
16k 733.4 55.6 20.8 GB view
32k 599.6 41.0 21.6 GB view
Batching Results
Batch Size TG tok/s Speedup
61.8 1.00×
124.1 2.01×
158.0 2.56×
130.6 2.11×