Walnoot 8B Instruct needs about 17.7 GB of memory at BF16 (a 16.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Walnoot 8B Instruct – Dutch instruction language model
Walnoot 8B Instruct is a Dutch language model built on Apertus‑8B‑2509. It is fine‑tuned for Dutch instruction tasks such as document question answering, information extraction, classification, summarisation and drafting of standard texts. The model is released under the Apache‑2.0 licence.
Good at
- Document question answering
- Information extraction
- Drafting standard texts
Limits
- Requires ~18 GB VRAM for BF16
- No vision support
- Limited to Dutch language tasks
Best for
- Business document drafting
- Legal text assistance
- Document QA in Dutch
Who it’s for. Professionals who need a Dutch‑centric LLM for business or legal documentation. The model is a tool, not a replacement for expert judgement.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 16.1 GB | 17.7 GB | Too big | Get file → |
The only available quant is BF16, 16.12 GB file size and ~17.7 GB VRAM at 8 k context. It is suitable for systems with at least 18 GB VRAM. No other quants are provided.
What GPU do you need for Walnoot 8B Instruct?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is BF16 (16.1 GB file, about 17.7 GB in use).
Which Walnoot 8B Instruct quant should you choose?
BF16 (16.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Walnoot 8B Instruct
How much VRAM does Walnoot 8B Instruct need?
About 17.7 GB at BF16 with an 8K context window. That is the 16.1 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 Walnoot 8B Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Walnoot 8B Instruct GGUF?
It depends on the quant: BF16 is 16.1 GB.
What context length does Walnoot 8B Instruct support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Walnoot 8B Instruct GGUF?
The files are on Hugging Face in the WAINUT/walnoot-8b-instruct repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Walnoot 8B Instruct 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 Walnoot 8B Instruct on 8 GB VRAM?
No. The BF16 quant requires about 17.7 GB VRAM at 8 k context, so 8 GB is insufficient.
Does the model support languages other than Dutch?
The model is specifically fine‑tuned for Dutch instruction tasks and is intended for Dutch language use.
Is the model open source?
Yes, it is released under the Apache‑2.0 licence and the weights are publicly available.