← Back to community benchmarks
DeepSeek-R1-Distill-Qwen-7B
Performance
1k
tokens
776.8
PP tok/s
29.5
TG tok/s
1320
TTFT (ms)
4.5
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 776.8 | 29.5 | 4.5 GB | current |
| 4k | 825.9 | 27.3 | 4.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.5 | 1.00× |
| 2× | 57.1 | 1.94× |
| 4× | 74.2 | 2.52× |