← Back to community benchmarks

Qwen3.5-4B

M3 (8c) · 16 GB · 4bit · 2026-03-11
Performance
1k
tokens
264.7
PP tok/s
32.6
TG tok/s
3868
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M3 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 264.7 32.6 3.9 GB current
4k 267.6 30.1 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
32.6 1.00×
58.1 1.78×
52.3 1.60×