KE

Kev-0.8B

KevGGUF by ggml-orgUpdated 2026-10-19
Download on Hugging Face
Parameters753M
Context256K
Layers24
Architectureqwen35
Smallest quant0.8 GB
Quick answer

Kev-0.8B needs about 1.7 GB of memory at Q8_0 (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.8 GB (Q8_0) to 1.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Kev-0.8B: a lightweight decision model for single-pass probability scoring

Kev-0.8B is a 0.753 B parameter decision model based on Qwen3.5. It reads a state and typed questions, returning calibrated probabilities without generating text. The model is designed for low‑memory environments such as laptops or 4 GB GPUs.

Good at

  • Single‑pass probability scoring
  • Low‑memory inference on 4 GB GPUs
  • Fast decision prototyping via System One API

Limits

  • No text generation or summarisation
  • Limited to English and states ≤65,536 tokens
  • Requires 8 k context for memory estimates

Best for

  • Document classification on small hardware
  • Fine‑tuning with limited compute
  • Prototyping System One API before scaling

Who it’s for. Developers needing a fast, low‑memory decision engine for document‑based tasks. It is suitable for prototyping, fine‑tuning, and deployment on laptops or modest GPUs where larger Kev models cannot fit.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.8 GB 1.7 GB
Fits Get file →
BF161.5 GB 2.4 GB
Fits Get file →

For 8 GB VRAM, use Q8_0 (0.81 GB, ~1.7 GB RAM at 8 k context). If more VRAM is available, BF16 (1.52 GB, ~2.4 GB RAM) offers higher precision. Memory estimates are approximate.

What GPU do you need for Kev-0.8B?

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 BF16 (1.5 GB file, about 2.4 GB in use).

Which Kev-0.8B quant should you choose?

Q8_0 (0.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters753M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized byggml-org
FamilyKev
Licenseapache-2.0
Downloads (HF)5,388
Last updated2026-10-19

Frequently asked questions about Kev-0.8B

How much VRAM does Kev-0.8B need?

About 1.7 GB at Q8_0 with an 8K context window. That is the 0.8 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-0.8B on an 8 GB GPU?

Yes, with BF16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kev-0.8B GGUF?

It depends on the quant: Q8_0 is 0.8 GB, BF16 is 1.5 GB.

What context length does Kev-0.8B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download Kev-0.8B GGUF?

The files are on Hugging Face in the ggml-org/Kev-0.8B-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-0.8B 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.

Does Kev-0.8B support text generation?

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

Other GGUFs of kev-0.8b

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Kev models

All Kev →

Other tiny models

All tiny models →