← Back to community benchmarks
DeepSeek-R1-Distill-Llama-8B
Performance
4k
tokens
197.5
PP tok/s
19.6
TG tok/s
20758
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 223.2 | 22.3 | 4.9 GB | view |
| 4k | 197.5 | 19.6 | 5.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.3 | 1.00× |
| 2× | 42.6 | 1.91× |