← Back to community benchmarks
DeepSeek-R1-Distill-Llama-70B
Performance
4k
tokens
167.2
PP tok/s
6.6
TG tok/s
24523
TTFT (ms)
39.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.20
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 168.9 | 7.0 | 37.9 GB | view |
| 4k | 167.2 | 6.6 | 39.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 7.0 | 1.00× |
| 2× | 12.7 | 1.81× |
| 4× | 16.0 | 2.29× |