← Back to community benchmarks
DeepSeek-R1-Distill-Qwen-32B
Performance
4k
tokens
346.2
PP tok/s
7.8
TG tok/s
11844
TTFT (ms)
34.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 310.3 | 8.0 | 33.2 GB | view |
| 4k | 346.2 | 7.8 | 34.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.0 | 1.00× |
| 2× | 14.8 | 1.85× |
| 4× | 21.6 | 2.70× |