KE

Kev kev-0.8b@bf75a6a8848ea6960ff2ed108d9ed44c2941174f

KevGGUF by espetroUpdated 2026-10-02
Download on Hugging Face
Parameters753M
Context256K
Layers24
Architectureqwen35
Smallest quant0.8 GB
Quick answer

Kev kev-0.8b@bf75a6a8848ea6960ff2ed108d9ed44c2941174f 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 (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Kev 0.8B v1.0 – a Qwen3.5 backbone with a calibrated pointer head

Kev 0.8B v1.0 is a Qwen3.5-0.8B backbone with a trained pointer head that returns calibrated probabilities for typed questions. It is built from Kev v1.0 and uses a LoRA adapter merged onto Qwen3.5-Base. The model is packaged as GGUF and supports reasoning and tools.

Good at

  • Calibrated probability output
  • Reasoning tasks
  • Tool invocation

Limits

  • No vision support
  • Requires 8k context for full performance
  • Apache-2.0 license

Best for

  • Decision‑making assistants
  • Typed question answering
  • Tool‑based workflows

Who it’s for. Developers building decision‑support systems that need reliable probability estimates. The model is suitable for applications that require typed question answering and tool integration without generating free‑form text.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.8 GB 1.7 GB
Fits Get file →
F161.5 GB 2.4 GB
Fits Get file →

For systems with 4 GB VRAM, use the Q8_0 quant (file size 0.81 GB, estimated memory 1.7 GB at 8k context). If more memory is available, the F16 quant (1.52 GB, 2.4 GB memory) offers higher precision. Both are approximate estimates.

What GPU do you need for Kev kev-0.8b@bf75a6a8848ea6960ff2ed108d9ed44c2941174f?

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 F16 (1.5 GB file, about 2.4 GB in use).

Which Kev kev-0.8b@bf75a6a8848ea6960ff2ed108d9ed44c2941174f 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 byespetro
FamilyKev
Licenseapache-2.0
Downloads (HF)236
Last updated2026-10-02

Frequently asked questions about Kev kev-0.8b@bf75a6a8848ea6960ff2ed108d9ed44c2941174f

How much VRAM does Kev kev-0.8b@bf75a6a8848ea6960ff2ed108d9ed44c2941174f 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 kev-0.8b@bf75a6a8848ea6960ff2ed108d9ed44c2941174f on an 8 GB GPU?

Yes, with F16: 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 kev-0.8b@bf75a6a8848ea6960ff2ed108d9ed44c2941174f GGUF?

It depends on the quant: Q8_0 is 0.8 GB, F16 is 1.5 GB.

What context length does Kev kev-0.8b@bf75a6a8848ea6960ff2ed108d9ed44c2941174f 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 kev-0.8b@bf75a6a8848ea6960ff2ed108d9ed44c2941174f GGUF?

The files are on Hugging Face in the espetro/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 kev-0.8b@bf75a6a8848ea6960ff2ed108d9ed44c2941174f 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 0.8B on 4 GB VRAM?

Yes, the Q8_0 quant uses about 1.7 GB of VRAM at 8k context, which fits within 4 GB. The F16 quant would exceed this limit.

Does Kev 0.8B support vision?

No, the model has no vision capabilities.

What license does Kev 0.8B use?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from espetro

All by espetro →

More Kev models

All Kev →

Other tiny models

All tiny models →