DeepSeek R1 Distill Llama 8B
8B parameters · 128k context · MIT License · released 2025-01-20
reasoningcodingchat
What to run it on in the US
Fully in memory at 64k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File |
|---|
Run it
Copy a command for the runtime you use.
No published builds to run yet.
Notes
Hugging Face Transformers is not directly supported; run via the DeepSeek-V3 repo tooling, and avoid system prompts (temperature 0.6 recommended). Distill variants inherit upstream Qwen-2.5 (Apache 2.0) or Llama 3.1/3.3 licences.
Questions
- What licence is DeepSeek R1 Distill Llama 8B released under?
- MIT License, which allows commercial use.