Llama 2 Models — Hardware Requirements
11 Llama 2 models from Meta and the community, from the smallest that runs in 0.3 GB of VRAM at Q4 up to 69.0B parameters. Every row links to full quantization tables and GPU compatibility.
All Llama 2 Models by Size
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Llama2 0B Unit Test | 770940 | 0.3 GB | 1K | ||
| Llama 2 7B Chat HF | 6.7B | 6.9 GB | — | ||
| Llama 2 7B HF | 6.7B | 6.9 GB | — | ||
| HarmBench Llama 2 13B Cls | 13.0B | 9.8 GB | 2K | ||
| Llama 2 13B Chat HF | 13.0B | 11.5 GB | — | ||
| Llama 2 13B HF | 13.0B | 11.5 GB | — | ||
| H2ogpt 4096 Llama2 70B Chat | 69.0B | 43.0 GB | 4K | ||
| Llama 2 70B HF | 69.0B | 50.2 GB | — | ||
| Llama 2 70B Chat HF | 69.0B | 50.2 GB | — |
How Llama 2 Compares — llmrun Composite Score
Llama 2 70B Chat HF is the highest-scoring Llama 2 model with an llmrun Composite Score of 48.6 — #106 among 106 open models. The top proprietary model, Gemini 4 Carbon, scores 158.6. Click a model to see its full benchmark breakdown.
Gemini 4 Carbon · proprietary158.6
GPT 6 Astra · proprietary156.2
Claude Opus 5.5 · proprietary153.0
GPT 6.1 Sol · proprietary151.7
GPT 6.1 Terra · proprietary150.1
Kimi K3.1 Pro142.8
MiMo V2.6 Pro RL133.3
Kimi K3132.7
MiMo V2.6 Flash RL131.9
GLM 5.3130.1
DeepSeek V4.1 Flash129.4
DeepSeek V4 Pro 0813129.2
Frequently Asked Questions
- How much VRAM do I need to run a Llama 2 model?
- The smallest Llama 2 model, Llama2 0B Unit Test, runs from 0.3 GB of VRAM at Q4_K_M. Larger family members need proportionally more — see the table above for every model.
- Which Llama 2 models can I run on a 16 GB GPU?
- 6 of 9 Llama 2 models fit in 16 GB of VRAM at Q4_K_M, including Llama 2 7B Chat HF, Llama 2 7B HF, Llama 2 13B Chat HF.
- What is the most popular Llama 2 model to run locally?
- Llama 2 7B Chat HF is the most downloaded Llama 2 model in local-friendly quantized formats. It runs from 6.9 GB of VRAM at Q4_K_M.
- How do Llama 2 models score on benchmarks?
- Llama 2 70B Chat HF leads the family with an llmrun Composite Score of 48.6, ranking #106 among 106 open models, while the top proprietary model, Gemini 4 Carbon, scores 158.6. See the comparison chart above for the full standings.