Llama Models — Hardware Requirements
11 Llama models from Meta and the community, from the smallest that runs in 0.0 GB of VRAM up to 8.2B parameters. Every row links to full quantization tables and GPU compatibility.
All Llama Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Llama 68M | 68M | 0.0 GB | 2K | ||
| Smol Llama 101M GQA | 101M | 0.4 GB | 1K | ||
| MobileLLaMA 1.4B Chat | 1.4B | 1.3 GB | 2K | ||
| Llama Guard 3 1B | 1.5B | 3.3 GB | — | ||
| Llama 7B | 6.7B | 3.1 GB | 2K | ||
| Llama XLAM 2 8B Fc R | 8B | 4.0 GB | 131K | ||
| Llama Guard 3 8B | 8.0B | 2.4 GB | — | ||
| Meta Llama Guard 2 8B | 8.0B | 17.7 GB | — | ||
| Llama Poro 2 8B Instruct | 8.0B | 4.0 GB | 8K | ||
| Llamatron 8B V1 | 8.0B | 4.0 GB | 131K | ||
| Llama Krikri 8B Instruct | 8.2B | 4.0 GB | 131K |
How Llama Compares — Benchmark Rating
Llama 7B is the highest-rated Llama model with an overall benchmark rating of 28.6/100 — #66 among 75 open models. The top proprietary model, GPT 5.5, scores 88.8. Click a model to see its full benchmark breakdown.
GPT 5.5 · proprietary88.8
Claude Opus 4.7 · proprietary87.6
Claude Fable 5 · proprietary86.6
GPT 5.4 · proprietary86.6
Claude Opus 4.8 · proprietary84.4
DeepSeek V4 Pro77.5
Qwen3.6 27B74.0
StableBeluga269.1
MiniMax M2.768.4
Llama 7B28.6
Frequently Asked Questions
- How much VRAM do I need to run a Llama model?
- The smallest Llama model, Llama 68M, runs from 0.0 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
- Which Llama models can I run on a 16 GB GPU?
- 10 of 11 Llama models fit in 16 GB of VRAM at some quantization, including Llama Guard 3 8B, Llama 68M, Llama 7B.
- What is the most popular Llama model to run locally?
- Llama Guard 3 8B is the most downloaded Llama model in local-friendly quantized formats. It runs from 2.4 GB of VRAM.
- How do Llama models score on benchmarks?
- Llama 7B leads the family with an overall benchmark rating of 28.6/100, ranking #66 among 75 open models, while the top proprietary model, GPT 5.5, scores 88.8. See the comparison chart above for the full standings.