Llama-3.3-70B-Instruct
Params
70.6 B
Context
—
Downloads 30d
351 K
Likes
3,198
Commercial use: conditional · llama3.3
Gated — accept licence
SAFETENSORS
8 languages
View on Hugging Face ↗
Download history
daily snapshots · 106 days
▲ 23 K in the last 30 days (7.2%)
396 K210 K
Oct 12Oct 22Nov 1Nov 10
932 K210 K
Aug 13Sep 12Oct 12Nov 10
932 K210 K
Jul 28Sep 1Oct 6Nov 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/llama-3-3-70b-instruct
{
"hf_id": "meta-llama/Llama-3.3-70B-Instruct",
"params_b": 70.55,
"context_length": null,
"license": { "id": "llama3.3", "commercial": "conditional" },
"downloads_30d": 350898,
"vram_estimates": [
{ "quant": "bf16", "gb": 166.3 }
],
"updated_at": "2026-07-28T18:04:43Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-11-10$0.71
input / 1M
$0.71
output / 1M
$0.71
cached input / 1M
$1.42
1M in + 1M out
- Context window
- 128,000 tokens
- Max output
- 115,200 tokens
- Providers
- 8
- Cheapest provider
- DeepInfra · $0.10 / $0.32
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / 11.9 / —
✓ Tool calling
✗ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- LlamaForCausalLM
- Parameters
- 70.6 B
- Tensor type
- BF16
- Licence
- llama3.3
- First seen on the Hub
- 2024-11-26
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model