kev_4b_unsloth_dynamic needs about 5.2 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 4.2 GB (Q4_K_M) to 8.4 GB (F16).
Kev-4B decision model for document classification and routing
Kev-4B is a decision model that scores typed questions over a single state. It returns calibrated probabilities for each option in one forward pass. The model is a LoRA adapter on Qwen3.5-4B-Base and is suitable for modest hardware.
Good at
- Document classification
- Confidence‑based routing
- Policy checks
Limits
- No text generation
- Not for legal or medical decisions without review
- Requires English states under 65,536 tokens
Best for
- Automated triage workflows
- Human‑in‑the‑loop review pipelines
- System One API replacements
Who it’s for. Developers needing fast, probabilistic decision scoring on documents. It is ideal for teams that want to integrate a lightweight decision engine into existing workflows without large GPU resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 4.2 GB | 5.2 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 5.5 GB | Fits | Get file → | |
| F16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (4.21 GB, ~5.2 GB memory at 8 k context). For 16 GB VRAM, Q8_0 (4.5 GB, ~5.5 GB memory) is also suitable. The larger F16 (8.44 GB) requires more memory and is not recommended for modest GPUs.
What GPU do you need for kev_4b_unsloth_dynamic?
These figures add the file size, an fp16 KV cache at an 8K context window 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 Q8_0 (4.5 GB file, about 5.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 5.5 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.4 GB file, about 10.0 GB in use).
Which kev_4b_unsloth_dynamic quant should you choose?
Q4_K_M is the usual starting point for kev_4b_unsloth_dynamic: it balances file size and quality well. Here it is a 4.2 GB file.
The Q8_0 file is 4.5 GB, about 1.1 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about kev_4b_unsloth_dynamic
How much VRAM does kev_4b_unsloth_dynamic need?
About 5.2 GB at Q4_K_M with an 8K context window. That is the 4.2 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_unsloth_dynamic on an 8 GB GPU?
Yes, with Q8_0: the 4.5 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of kev_4b_unsloth_dynamic GGUF?
It depends on the quant: Q4_K_M is 4.2 GB, Q8_0 is 4.5 GB, F16 is 8.4 GB.
Where can I download kev_4b_unsloth_dynamic GGUF?
The files are on Hugging Face in the mys/kev-4b-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_unsloth_dynamic 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 on an 8 GB GPU?
Yes, the Q4_K_M quantization file is 4.21 GB and requires about 5.2 GB of VRAM at 8 k context.
Does Kev-4B support text generation?
No, it only scores options and does not generate text.
What license does Kev-4B use?
Apache‑2.0, the same as the parent model.