KE

Kev-27B Artemis 12.3GB

KevGGUF by turintechUpdated 2026-10-26
Download on Hugging Face
Parameters25.6B
Context256K
Layers64
Architectureqwen35
Smallest quant12.3 GB
Quick answer

Kev-27B Artemis 12.3GB needs about 16.6 GB of memory at IQ4_XS (a 13.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 12.3 GB (Q3_K_M) to 14.6 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Kev-27B Artemis 12.3GB – a decision model for typed document scoring

Kev-27B Artemis is a 27B parameter decision model that reads a state and a set of typed questions, returning calibrated probabilities for each option. It is designed for classification, routing, triage, and policy checks on English documents up to 65,536 tokens. The model is available in GGUF format and runs on llama.cpp.

Good at

  • Typed decision scoring
  • Confidence‑based workflow automation
  • Single‑pass probability generation

Limits

  • No text generation or chat
  • Requires >80 GB GPU or ~96 GB RAM
  • Only English language support

Best for

  • Document triage pipelines
  • Automated routing with human review
  • Policy eligibility checks

Who it’s for. Developers building decision‑making services that need fast, probabilistic scoring of documents. The model is suitable for self‑hosted, offline deployments where data privacy is critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M12.3 GB 15.0 GB
Too big Get file →
IQ4_XS13.9 GB 16.6 GB
Too big Get file →
Q4_K_S14.6 GB 17.2 GB
Too big Get file →

For 8 GB VRAM, use the IQ4_XS quant (13.91 GB file, ~16.6 GB memory at 8k context). For 16 GB VRAM, Q4_K_S (14.56 GB file, ~17.2 GB memory) is suitable. Larger GPUs can run the full‑precision 12.31 GB file with ~15 GB memory at 8k context.

What GPU do you need for Kev-27B Artemis 12.3GB?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q3_K_M (12.3 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_S (14.6 GB file, about 17.2 GB in use).

Which Kev-27B Artemis 12.3GB quant should you choose?

IQ4_XS (13.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q3_K_M at 12.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters25.6B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized byturintech
FamilyKev
Licenseapache-2.0
Downloads (HF)4,264
Last updated2026-10-26

Frequently asked questions about Kev-27B Artemis 12.3GB

How much VRAM does Kev-27B Artemis 12.3GB need?

About 16.6 GB at IQ4_XS with an 8K context window. That is the 13.9 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-27B Artemis 12.3GB on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kev-27B Artemis 12.3GB GGUF?

It depends on the quant: Q3_K_M is 12.3 GB, IQ4_XS is 13.9 GB, Q4_K_S is 14.6 GB.

What context length does Kev-27B Artemis 12.3GB support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Kev-27B Artemis 12.3GB GGUF?

The files are on Hugging Face in the turintech/Kev-27B-Artemis-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-27B Artemis 12.3GB 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-27B Artemis on an 8 GB GPU?

Yes, using the IQ4_XS quant file (13.91 GB) which requires about 16.6 GB memory at 8k context. The model will need a larger VRAM than the file size due to runtime overhead.

Does the model support vision or multi‑modal inputs?

No. Kev-27B Artemis is a text‑only decision model and does not process images or other modalities.

What license applies to the model?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Other GGUFs of kev-27b

Similar models

Browse all →

More from turintech

All by turintech →

More Kev models

All Kev →

Other medium models

All medium models →