h2o-danube3-500m-chat
h2o-danube3-500m-chat is a chat fine-tuned model by H2O.ai with 500 million parameters. We release two versions of this model:
Params
514 M
Context
8,192
Downloads 30d
179 K
Likes
43
Download history
tracking started — chart appears after 7 days of snapshots (6 recorded)179 K downloads in the last 30 days
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 | 1.0 GB | 1.7 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/h2o-danube3-500m-chat
{
"hf_id": "h2oai/h2o-danube3-500m-chat",
"params_b": 0.51,
"context_length": 8192,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 179005,
"vram_estimates": [
{ "quant": "bf16", "gb": 1.7 }
],
"updated_at": "2026-10-20T01:00:32Z"
}
Specifications
- Architecture
- LlamaForCausalLM
- Parameters
- 514 M
- Tensor type
- BF16
- Context length
- 8,192
- Vocabulary
- 32,000
- Layers / heads
- 16 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2024-07-04
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model