←Back to models
Checked Active: 2026-10-15
Meta
Llama 3.3 70B (local)
Proven general model if you have 48 GB or more of memory. Older than Muse Glimmer but widely supported.
Evaluation Analysis: Tools, text only. Plan on RAM or VRAM of roughly the download size plus 2 to 4 GB for context.
Context Window128K
Input Price / 1MFree (local)
Output Price / 1MFree (local)
Release Date2024-12
Run it locally
ollama run llama3.3- Ollama tag
- llama3.3:70b
- LM Studio name
- Search "Llama 3.3 70B" in LM Studio (community GGUF)
- Download size by quantization
- 43 GB Q4 / 75 GB Q8
- License
- Llama 3.3 Community License
Memory needed is roughly the download size plus 2 to 4 GB for context. See how to run AI locally.
Specs and prices checked 2026-10-15 against the official page.