← Back to community benchmarks
Qwen2.5-Coder-32B-Instruct
Performance
1k
tokens
373.1
PP tok/s
14.8
TG tok/s
2745
TTFT (ms)
17.9
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
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 373.1 | 14.8 | 17.9 GB | current |
| 4k | 379.7 | 13.6 | 19.0 GB | view |