← Back to community benchmarks

Qwen3.5-4B

M1 Pro (14c) · 32 GB · 4bit · 2026-03-10
Performance
1k
tokens
252.8
PP tok/s
49.5
TG tok/s
4051
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 32 GB
GPU Cores 14
Software
oMLX v0.2.6
macOS macOS 26.2
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
1× 49.5 1.00×
2× 55.9 1.13×
4× 59.4 1.20×
8× 48.4 0.98×