← Back to community benchmarks
DeepSeek-R1-Distill-Qwen-1.5B
Performance
4k
tokens
1,031
PP tok/s
61.6
TG tok/s
3974
TTFT (ms)
1.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 989.7 | 76.0 | 1.6 GB | view |
| 4k | 1,031 | 61.6 | 1.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 76.0 | 1.00× |
| 2× | 150.5 | 1.98× |