← Back to community benchmarks
DeepSeek-R1-Distill-Qwen-7B
Performance
4k
tokens
251.3
PP tok/s
22.3
TG tok/s
16313
TTFT (ms)
4.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.8rc1
macOS
macOS 15.7.7
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 247.3 | 24.2 | 4.6 GB | view |
| 4k | 251.3 | 22.3 | 4.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.2 | 1.00× |
| 2× | 47.0 | 1.94× |
| 4× | 59.8 | 2.47× |