← Back to community benchmarks
DeepSeek-R1-Distill-Qwen-14B
Performance
8k
tokens
103.3
PP tok/s
9.2
TG tok/s
79290
TTFT (ms)
9.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.12
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 124.7 | 12.0 | 8.4 GB | view |
| 4k | 117.9 | 10.7 | 9.0 GB | view |
| 8k | 103.3 | 9.2 | 9.7 GB | current |
| 16k | 91.1 | 7.4 | 11.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.0 | 1.00× |
| 2× | 23.7 | 1.97× |
| 4× | 28.5 | 2.38× |