Meta-Llama-3-70B
Params
70.6 B
Context
—
Downloads 30d
136 K
Likes
888
Commercial use: conditional · llama3
Gated — accept licence
SAFETENSORS
1 languages
View on Hugging Face ↗
Download history
daily snapshots · 85 days
▲ 41 K in the last 30 days (23.2%)
177 K132 K
Oct 12Oct 22Nov 1Nov 10
177 K132 K
Aug 18Sep 15Oct 13Nov 10
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 | bf16 | 141.1 GB | 166.3 GB | ❌ Won’t fit |
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/meta-llama-3-70b
{
"hf_id": "meta-llama/Meta-Llama-3-70B",
"params_b": 70.55,
"context_length": null,
"license": { "id": "llama3", "commercial": "conditional" },
"downloads_30d": 135686,
"vram_estimates": [
{ "quant": "bf16", "gb": 166.3 }
],
"updated_at": "2026-08-18T01:00:41Z"
}
Specifications
- Architecture
- LlamaForCausalLM
- Parameters
- 70.6 B
- Tensor type
- BF16
- Licence
- llama3
- First seen on the Hub
- 2024-04-17
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-18
Compare with any text-generation model