← Back to community benchmarks

Qwen3-14B

M1 Pro (16c) · 32 GB · 4bit · 2026-03-13
Performance
1k
tokens
77.3
PP tok/s
18.0
TG tok/s
13241
TTFT (ms)
8.5
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.2.10
macOS macOS 15.7.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 77.3 18.0 8.5 GB current
4k 77.8 16.0 9.0 GB view
Batching Results
Batch Size TG tok/s Speedup
18.0 1.00×
19.2 1.07×
20.4 1.13×