← Back to community benchmarks

Qwen3.5-4B

M1 Pro (16c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
286.8
PP tok/s
21.1
TG tok/s
14284
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 16 GB
GPU Cores 16
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 282.4 25.0 4.0 GB view
4k 286.8 21.1 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
25.0 1.00×
46.8 1.87×
64.3 2.57×