← Back to community benchmarks

Qwen3.5-4B

M1 Pro (14c) · 16 GB · 4bit · 2026-03-09
Performance
1k
tokens
253.0
PP tok/s
47.5
TG tok/s
4048
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 16 GB
GPU Cores 14
Software
oMLX v0.2.6
macOS macOS 15.7.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 253.0 47.5 4.0 GB current
4k 255.0 46.5 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
47.5 1.00×
55.5 1.17×
57.4 1.21×