← Back to community benchmarks

Qwen3.5-4B

M3 (10c) · 16 GB · 4bit · 2026-03-09
Performance
1k
tokens
340.1
PP tok/s
32.4
TG tok/s
3011
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M3 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 340.1 32.4 3.9 GB current
4k 329.5 31.8 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
32.4 1.00×
60.1 1.85×
25.3 0.78×