KE

Kev kev-9b@db029f08b290afd9fee4aa4bbcd9ae48602d1eb0

KevGGUF by espetroUpdated 2026-10-02
Download on Hugging Face
Parameters8.96B
Context256K
Layers32
Architectureqwen35
Smallest quant9.5 GB
Quick answer

Kev kev-9b@db029f08b290afd9fee4aa4bbcd9ae48602d1eb0 needs about 11.1 GB of memory at Q8_0 (a 9.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 9.5 GB (Q8_0) to 17.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Kev-9B: a Qwen3.5-9B backbone with a calibrated pointer head for decision tasks

Kev-9B is a 8.96B parameter model built on Qwen3.5-9B. It includes a trained pointer head that returns calibrated probabilities for typed questions. The model is packaged as GGUF and supports reasoning and tools.

Good at

  • Calibrated probability outputs
  • Reasoning tasks
  • Tool integration

Limits

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

Best for

  • Decision support systems
  • Typed question answering
  • Tool‑enabled workflows

Who it’s for. Developers building decision‑making applications that need reliable probability estimates. The model is suitable for local deployment with llama.cpp and can be used in browser demos via espetro.github.io/llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_09.5 GB 11.1 GB
Too big Get file →
F1617.9 GB 19.5 GB
Too big Get file →

For 8GB VRAM, use the Q8_0 quant (file size 9.54 GB, estimated 11.1 GB memory at 8k context). If more memory is available, the F16 quant (17.93 GB, 19.5 GB memory) provides higher precision.

What GPU do you need for Kev kev-9b@db029f08b290afd9fee4aa4bbcd9ae48602d1eb0?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.9 GB file, about 19.5 GB in use).

Which Kev kev-9b@db029f08b290afd9fee4aa4bbcd9ae48602d1eb0 quant should you choose?

Q8_0 (9.5 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
Parameters8.96B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byespetro
FamilyKev
Licenseapache-2.0
Downloads (HF)194
Last updated2026-10-02

Frequently asked questions about Kev kev-9b@db029f08b290afd9fee4aa4bbcd9ae48602d1eb0

How much VRAM does Kev kev-9b@db029f08b290afd9fee4aa4bbcd9ae48602d1eb0 need?

About 11.1 GB at Q8_0 with an 8K context window. That is the 9.5 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-9b@db029f08b290afd9fee4aa4bbcd9ae48602d1eb0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kev kev-9b@db029f08b290afd9fee4aa4bbcd9ae48602d1eb0 GGUF?

It depends on the quant: Q8_0 is 9.5 GB, F16 is 17.9 GB.

What context length does Kev kev-9b@db029f08b290afd9fee4aa4bbcd9ae48602d1eb0 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 kev-9b@db029f08b290afd9fee4aa4bbcd9ae48602d1eb0 GGUF?

The files are on Hugging Face in the espetro/kev-9b-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-9b@db029f08b290afd9fee4aa4bbcd9ae48602d1eb0 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-9B on 8 GB VRAM?

Yes, the Q8_0 quant uses about 11.1 GB of VRAM at 8k context, which fits in 8 GB with some overhead.

Does Kev-9B support image inputs?

No, Kev-9B does not include vision capabilities.

What license applies to Kev-9B?

Kev-9B is released under Apache-2.0.

Similar models

Browse all →

More from espetro

All by espetro →

More Kev models

All Kev →

Other small models

All small models →