← Back to community benchmarks

Qwen3-4B

M4 (8c) · 16 GB · 4bit · 2026-03-09
Performance
4k
tokens
265.1
PP tok/s
30.4
TG tok/s
15448
TTFT (ms)
3.2
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 290.2 36.3 2.8 GB view
4k 265.1 30.4 3.2 GB current
Batching Results
Batch Size TG tok/s Speedup
36.3 1.00×
65.7 1.81×
69.2 1.91×