h2o-danube3-500m-chat needs about 1.2 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 0.2 GB (IQ3_M) to 2.1 GB (F32).
h2o-danube3-500m-chat – a 500 M parameter chat model
h2o-danube3-500m-chat is a chat‑fine‑tuned Llama‑based model with 500 M parameters. It supports a context length of 8 192 tokens and uses the Mistral tokenizer. The model is released under the Apache‑2.0 license.
Good at
- Chat‑style dialogue
- Short‑form content generation
- Low‑resource inference
Limits
- No vision support
- Requires 8 192 token context
- No system prompt support
Best for
- Building lightweight chatbots
- Running on edge devices
- Educational demos
Who it’s for. Developers and researchers needing a small, chat‑optimized Llama model that can run offline. The model is suitable for projects with limited GPU memory and for those who prefer an Apache‑2.0 licensed model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_M | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_L | 0.3 GB | 1.2 GB | Fits | Get file → | |
| IQ4_XS | 0.3 GB | 1.2 GB | Fits | Get file → | |
| Q4_K_S | 0.3 GB | 1.2 GB | Fits | Get file → | |
| Q4_K_M | 0.3 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_XL | 0.3 GB | 1.2 GB | Fits | Get file → | |
| Q4_K_L | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_S | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_M | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_L | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q6_K | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q6_K_L | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q8_0 | 0.5 GB | 1.4 GB | Fits | Get file → | |
| F32 | 2.1 GB | 3.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_S (file size 0.30 GB, estimated 1.2 GB memory). For 4 GB VRAM, use IQ3_M (0.25 GB, 1.2 GB memory). For higher quality, Q8_0 (0.55 GB, 1.4 GB memory) fits in 8 GB VRAM. Estimates are approximate.
What GPU do you need for h2o-danube3-500m-chat?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F32 (2.1 GB file, about 3.0 GB in use).
Which h2o-danube3-500m-chat quant should you choose?
Q4_K_M is the usual starting point for h2o-danube3-500m-chat: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ3_M at 0.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about h2o-danube3-500m-chat
How much VRAM does h2o-danube3-500m-chat need?
About 1.2 GB at Q4_K_M with an 8K context window. That is the 0.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run h2o-danube3-500m-chat on an 8 GB GPU?
Yes, with F32: the 2.1 GB file needs about 3.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of h2o-danube3-500m-chat GGUF?
It depends on the quant: IQ3_M is 0.2 GB, Q3_K_L is 0.3 GB, IQ4_XS is 0.3 GB, Q4_K_S is 0.3 GB, Q4_K_M is 0.3 GB, Q3_K_XL is 0.3 GB and 8 more.
What context length does h2o-danube3-500m-chat support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.4 GB at 8K.
Where can I download h2o-danube3-500m-chat GGUF?
The files are on Hugging Face in the bartowski/h2o-danube3-500m-chat-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does h2o-danube3-500m-chat use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run h2o-danube3-500m-chat on 8 GB VRAM?
Yes, use a quant such as Q4_K_S or IQ3_M, which require about 1.2 GB of VRAM at 8 192 context.
Does the model support system prompts?
No, the model does not support a system prompt.
What license does the model use?
The model is released under the Apache‑2.0 license.