← Back to community benchmarks

Qwen3.5-4B

M4 (8c) · 16 GB · 4bit · 2026-04-05
Performance
1k
tokens
291.7
PP tok/s
37.5
TG tok/s
3510
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.1
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 291.7 37.5 3.3 GB current
4k 296.4 35.4 4.0 GB view
Batching Results
Batch Size TG tok/s Speedup
37.5 1.00×
65.8 1.75×
70.2 1.87×