kev 4b demo needs about 4.1 GB of memory at its main file (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Kev-4B demo quant: Qwen3.5-4B backbone with decision head
Kev-4B demo quant is a 4.21B parameter model based on Qwen3.5. It provides decision outputs such as `noul`, `choice`, and `score` with calibrated probabilities. The model is quantized for fast download and runs client‑side via WebAssembly.
Good at
- Decision‑making with calibrated probabilities
- Reasoning tasks
- Tool usage
Limits
- No text generation
- Limited to 262144 context tokens
- Requires 4.1 GB VRAM at 8k context (approx.)
Best for
- Quick decision‑model trials
- WebAssembly demos
- Low‑latency inference on modest GPUs
Who it’s for. Developers and researchers needing a lightweight decision model for prototyping. It is suitable for testing decision logic without full‑precision deployment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.6 GB | 4.1 GB | Fits | Get file → |
The only available quant is Q4_K_M, 2.55 GB download. It requires roughly 4.1 GB VRAM at 8k context. For larger context or higher precision, use the full‑precision artifact espetro/kev-4b-gguf.
What GPU do you need for kev 4b demo?
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: the best quant that fits is the main file (2.6 GB file, about 4.1 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about kev 4b demo
How much VRAM does kev 4b demo need?
About 4.1 GB at its main file with an 8K context window. That is the 2.6 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 kev 4b demo on an 8 GB GPU?
Yes, with the smaller files: the 2.6 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of kev 4b demo GGUF?
It depends on the quant: file is 2.6 GB.
What context length does kev 4b demo support?
The GGUF header lists a trained context length of 262,144 tokens (256K). 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 kev 4b demo GGUF?
The files are on Hugging Face in the espetro/kev-4b-demo-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 kev 4b demo 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 Kev-4B demo on 8 GB VRAM?
Yes, it requires about 4.1 GB VRAM at 8k context, so 8 GB is sufficient.
Does this model support text generation?
No, it only outputs decision tokens like `noul`, `choice`, and `score`.
Is the quantization stable?
It is a demo quant; probabilities may drift compared to the full‑precision model.