← Back to community benchmarks
DeepSeek-R1-Distill-Qwen-1.5B
Performance
1k
tokens
989.7
PP tok/s
76.0
TG tok/s
1036
TTFT (ms)
1.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 989.7 | 76.0 | 1.6 GB | current |
| 4k | 1,031 | 61.6 | 1.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 76.0 | 1.00× |
| 2× | 150.5 | 1.98× |