← Back to community benchmarks

Qwen3-14B

M4 (8c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
81.2
PP tok/s
9.9
TG tok/s
50432
TTFT (ms)
8.9
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 78.4 10.5 8.4 GB view
4k 81.2 9.9 8.9 GB current
Batching Results
Batch Size TG tok/s Speedup
10.5 1.00×
22.0 2.10×
22.5 2.14×