← Back to community benchmarks
Qwen2.5-Coder-14B-Instruct
Performance
4k
tokens
829.4
PP tok/s
28.9
TG tok/s
4938
TTFT (ms)
9.2
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 829.1 | 31.5 | 8.5 GB | view |
| 4k | 829.4 | 28.9 | 9.2 GB | current |