KE

Kev 4B

KevGGUF by ggml-orgUpdated 2026-10-19
Download on Hugging Face
Parameters4.2B
Context256K
Layers32
Architectureqwen35
Smallest quant3.0 GB
Quick answer

Kev 4B needs about 4.6 GB of memory at Q4_K_M (a 3.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 3.0 GB (Q4_K_M) to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Kev 4B – a lightweight decision model for document classification and routing

Kev 4B is a decision model built on Qwen3.5-4B-Base. It reads a state and a set of typed questions, returning calibrated probabilities for each option. The model is designed for classification, routing, triage, and policy checks on modest hardware.

Good at

  • Fast probability scoring for document decisions
  • Low VRAM footprint with Q4_K_M
  • Easy integration via System One API

Limits

  • No text generation or chat
  • Requires English states under 65,536 tokens
  • Not suitable for legal or medical fully automated decisions

Best for

  • Document classification workflows
  • Confidence‑based triage systems
  • Self‑hosted System One replacements

Who it’s for. Developers needing quick, probabilistic decisions on documents. It works well on a single 24 GB GPU or a 32 GB Apple Silicon Mac and can be fine‑tuned with Kev training scripts.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M3.0 GB 4.6 GB
Fits Get file →
Q8_04.5 GB 6.1 GB
Fits Get file →
BF168.4 GB 10.0 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (3.03 GB, ~4.6 GB memory at 8 k context). If 16 GB VRAM is available, Q8_0 (4.48 GB, ~6.1 GB memory) provides higher precision. BF16 requires 8.43 GB and ~10 GB memory, suitable for larger GPUs.

What GPU do you need for Kev 4B?

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 Q4_K_M (3.0 GB file, about 4.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).

Which Kev 4B quant should you choose?

Q4_K_M is the usual starting point for Kev 4B: it balances file size and quality well. Here it is a 3.0 GB file.

The Q8_0 file is 4.5 GB, about 1.5 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

Architectureqwen35
Parameters4.2B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byggml-org
FamilyKev
Licenseapache-2.0
Downloads (HF)54,266
Last updated2026-10-19

Frequently asked questions about Kev 4B

How much VRAM does Kev 4B need?

About 4.6 GB at Q4_K_M with an 8K context window. That is the 3.0 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 on an 8 GB GPU?

Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kev 4B GGUF?

It depends on the quant: Q4_K_M is 3.0 GB, Q8_0 is 4.5 GB, BF16 is 8.4 GB.

What context length does Kev 4B 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 GGUF?

The files are on Hugging Face in the ggml-org/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 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 8 GB VRAM?

Yes, using the Q4_K_M quantization which fits in 8 GB VRAM and uses about 4.6 GB of memory at 8 k context.

Does Kev 4B support text generation?

No, it only scores options and does not generate text.

What languages does Kev 4B support?

It is designed for English states and does not support other languages.

Other GGUFs of kev-4b

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Kev models

All Kev →

Other small models

All small models →