← Back to community benchmarks

Qwen3.5-4B

M3 Pro (14c) · 18 GB · 4bit · 2026-03-10
Performance
8k
tokens
476.7
PP tok/s
42.0
TG tok/s
17183
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip M3 Pro (14c)
Memory 18 GB
GPU Cores 14
Software
oMLX v0.2.6
macOS macOS 15.3.2
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 491.4 47.7 4.0 GB view
4k 485.9 43.0 4.2 GB view
8k 476.7 42.0 4.6 GB current
Batching Results
Batch Size TG tok/s Speedup
47.7 1.00×
91.0 1.91×
53.7 1.13×