← Back to community benchmarks
DeepSeek-R1-Distill-Llama-8B-4bit
Performance
1k
tokens
204.9
PP tok/s
18.7
TG tok/s
5017
TTFT (ms)
4.9
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 | 204.9 | 18.7 | 4.9 GB | current |
| 4k | 209.8 | 17.1 | 5.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.7 | 1.00× |
| 2× | 36.4 | 1.95× |