← Back to community benchmarks
DeepSeek-R1-Distill-Qwen-1.5B
Performance
1k
tokens
1,089
PP tok/s
31.2
TG tok/s
941
TTFT (ms)
3.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,089 | 31.2 | 3.7 GB | current |
| 4k | 1,062 | 29.8 | 3.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.2 | 1.00× |
| 2× | 40.4 | 1.29× |
| 4× | 78.9 | 2.53× |