← Back to community benchmarks

Qwen2.5-Coder-14B-Instruct

M3 Max (30c) · 36 GB · 4bit · 2026-04-15
Performance
1k
tokens
320.7
PP tok/s
30.8
TG tok/s
3193
TTFT (ms)
8.5
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.3.5.dev1
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 320.7 30.8 8.5 GB current
4k 315.9 27.2 9.2 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 30.8 1.00×
2× 51.5 1.67×
4× 63.8 2.07×