Will this model run on your hardware?
Can I run Meta: Llama 3.3 70B Instruct locally?
- 71B parameters
- licence: llama3.3
- Weights: meta-llama/Llama-3.3-70B-Instruct · GGUF: MaziyarPanahi/Llama-3.3-70B-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 | 75.0 GB |
| Q6_K | 57.9 GB |
| Q5_K_M | 49.9 GB |
| Q4_K_M | 42.5 GB |
| Q3_K_M | 34.3 GB |
| Q2_K | 26.4 GB |
Run it locally
ollama run hf.co/MaziyarPanahi/Llama-3.3-70B-Instruct-GGUF:Q4_K_M
llama serve -hf MaziyarPanahi/Llama-3.3-70B-Instruct-GGUF:Q4_K_M