← Back to community benchmarks

Qwen3.5-4B

M1 Pro (16c) · 32 GB · 4bit · 2026-03-09
Performance
4k
tokens
292.5
PP tok/s
49.3
TG tok/s
14005
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 292.6 53.8 4.0 GB view
4k 292.5 49.3 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
53.8 1.00×
62.1 1.15×
66.2 1.23×