Llama-2-7b-hf
Params
6.7 B
Context
—
Downloads 30d
806 K
Likes
2,414
Commercial use: conditional · llama2
Gated — accept licence
SAFETENSORS
1 languages
View on Hugging Face ↗
Download history
daily snapshots · 56 days
▲ 19 K in the last 30 days (2.4%)
812 K742 K
Aug 23Sep 2Sep 12Sep 21
812 K727 K
Jul 28Aug 15Sep 3Sep 21
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f16 | 13.5 GB | 16.3 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/llama-2-7b-hf
{
"hf_id": "meta-llama/Llama-2-7b-hf",
"params_b": 6.74,
"context_length": null,
"license": { "id": "llama2", "commercial": "conditional" },
"downloads_30d": 805724,
"vram_estimates": [
{ "quant": "f16", "gb": 16.3 }
],
"updated_at": "2026-07-28T18:04:15Z"
}
Specifications
- Architecture
- LlamaForCausalLM
- Parameters
- 6.7 B
- Tensor type
- F16
- Licence
- llama2
- First seen on the Hub
- 2023-07-13
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any text-generation model