Will this model run on your hardware?
Can I run Meta: Llama 4 Scout locally?
- 109B parameters
- licence: other
- #63 in the AIContenders model ranking
- Weights: meta-llama/Llama-4-Scout-17B-16E-Instruct · GGUF: unsloth/Llama-4-Scout-17B-16E-Instruct-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 |
|---|---|
| Q8_0 | 114.5 GB |
| Q6_K | 88.4 GB |
| Q5_K_M | 76.5 GB |
| Q4_K_M | 65.4 GB |
| Q3_K_M | 51.8 GB |
| Q2_K | 39.6 GB |
Run it locally
ollama run hf.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF:Q4_K_M
llama serve -hf unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF:Q4_K_M