Will this model run on your hardware?
Can I run Sao10K: Llama 3 8B Lunaris locally?
- 8.0B parameters
- context up to 8K
- licence: llama3
- Weights: Sao10K/L3-8B-Lunaris-v1 · GGUF: mradermacher/L3-8B-Lunaris-v1-i1-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q6_K | 6.6 GB |
| Q5_K_M | 5.7 GB |
| Q4_K_M | 4.9 GB |
| Q3_K_M | 4.0 GB |
| Q2_K | 3.2 GB |
Run it locally
ollama run hf.co/mradermacher/L3-8B-Lunaris-v1-i1-GGUF:Q4_K_M
llama serve -hf mradermacher/L3-8B-Lunaris-v1-i1-GGUF:Q4_K_M
LM Studio: open mradermacher/L3-8B-Lunaris-v1-i1-GGUF