← Back to community benchmarks

Qwen3.5-4B

M4 (8c) · 16 GB · 4bit · 2026-03-09
Performance
1k
tokens
305.1
PP tok/s
37.0
TG tok/s
3357
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
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 305.1 37.0 3.9 GB current
4k 295.9 31.9 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
37.0 1.00×
62.8 1.70×
57.6 1.56×