KE

Kev kev-4b@6cfce5c2fa4b4bd64026336ab649c5ca78857d52

KevGGUF by espetroUpdated 2026-10-02
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant4.5 GB
Quick answer

Kev kev-4b@6cfce5c2fa4b4bd64026336ab649c5ca78857d52 needs about 6.1 GB of memory at Q8_0 (a 4.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 4.5 GB (Q8_0) to 8.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Kev-4B: a Qwen3.5-4B backbone with a calibrated pointer head

Kev-4B is a Qwen3.5-4B backbone with a trained pointer head that returns calibrated probabilities for typed questions. It is a decision model that does not generate text but provides calibrated answers. The model is licensed under apache-2.0.

Good at

  • Reasoning tasks
  • Tool usage
  • Calibrated probability outputs

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No mixture of experts

Best for

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

Who it’s for. Developers building decision‑making applications that need calibrated probabilities. The model is suitable for local deployment with llama.cpp or similar GGUF runtimes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_04.5 GB 6.1 GB
Fits Get file →
F168.4 GB 10.0 GB
Too big Get file →

For a 8 GB VRAM budget, use the Q8_0 quant (file size 4.49 GB, estimated 6.1 GB at 8k context). If more memory is available, the F16 quant (8.43 GB, 10 GB at 8k context) provides higher precision. Estimates are approximate.

What GPU do you need for Kev kev-4b@6cfce5c2fa4b4bd64026336ab649c5ca78857d52?

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: 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 F16 (8.4 GB file, about 10.0 GB in use).

Which Kev kev-4b@6cfce5c2fa4b4bd64026336ab649c5ca78857d52 quant should you choose?

Q8_0 (4.5 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
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byespetro
FamilyKev
Licenseapache-2.0
Downloads (HF)235
Last updated2026-10-02

Frequently asked questions about Kev kev-4b@6cfce5c2fa4b4bd64026336ab649c5ca78857d52

How much VRAM does Kev kev-4b@6cfce5c2fa4b4bd64026336ab649c5ca78857d52 need?

About 6.1 GB at Q8_0 with an 8K context window. That is the 4.5 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-4b@6cfce5c2fa4b4bd64026336ab649c5ca78857d52 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 kev-4b@6cfce5c2fa4b4bd64026336ab649c5ca78857d52 GGUF?

It depends on the quant: Q8_0 is 4.5 GB, F16 is 8.4 GB.

What context length does Kev kev-4b@6cfce5c2fa4b4bd64026336ab649c5ca78857d52 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-4b@6cfce5c2fa4b4bd64026336ab649c5ca78857d52 GGUF?

The files are on Hugging Face in the espetro/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 kev-4b@6cfce5c2fa4b4bd64026336ab649c5ca78857d52 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, the Q8_0 quant uses about 6.1 GB at 8k context, fitting within an 8 GB VRAM budget.

Does Kev-4B support vision?

No, the model has no vision capabilities.

What is the context length of Kev-4B?

The trained context length is 262144 tokens.

Similar models

Browse all →

More from espetro

All by espetro →

More Kev models

All Kev →

Other small models

All small models →