← Back to community benchmarks

Qwen2.5-Coder-14B-Instruct

M3 (10c) · 24 GB · 4bit · 2026-03-11
Performance
1k
tokens
102.6
PP tok/s
10.5
TG tok/s
9984
TTFT (ms)
8.4
Peak mem (GB)
Hardware
Chip M3 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.7.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 102.6 10.5 8.4 GB current
4k 83.6 8.4 9.0 GB view
Batching Results
Batch Size TG tok/s Speedup
10.5 1.00×
13.4 1.28×
13.1 1.25×