← Back to community benchmarks
DeepSeek-R1-Distill-Qwen-32B
Performance
1k
tokens
381.2
PP tok/s
14.8
TG tok/s
2689
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 | 381.2 | 14.8 | 17.9 GB | current |
| 4k | 381.5 | 13.9 | 19.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.8 | 1.00× |
| 2× | 26.5 | 1.79× |
| 4× | 34.7 | 2.34× |