Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

JEV-27B-VL-Uncensored-GGUF

Static GGUF quantizations by mradermacher of SargeDev's JEV-27B-VL-Uncensored vision decision model.

ModelApache-2.0
Open source ↗

Overview

This Hugging Face repository provides static GGUF quantizations, made by mradermacher, of SargeDev/JEV-27B-VL-Uncensored, an abliterated vision variant of a Qwen3.8 27B decision model distilled from Jev 1.13 on jev-distill-corpus-v3. Tags list noul, choice and score typed decisions with calibrated probabilities.

It targets local users of llama.cpp-compatible tools. Quantizations start at Q2_K (10.8 GB), with multimodal projector files (0.7-1.0 GB) for image input. As with the text-only sibling, the card has no description beyond tags, and producing typed decision probabilities requires tooling that implements the model's readout rather than plain chat. The text-only sibling, JEV-27B-Uncensored-GGUF, is published by the same quantizer, and users should check the upstream SargeDev model card for intended use and any evaluation results before deploying it.

What the decision model decides

TypeQuestionAnswers
OtherSame typed noul/choice/score decisions over text and images as the upstream model(inferred)—

How it works

  1. Choose a quantization and the mmproj file
  2. Download from Hugging Face
  3. Run with a llama.cpp build that supports the decision readout and vision

Strengths

  • Local vision decision model in several sizes
  • Apache-2.0 licence

Caveats

  • No upstream description
  • Uncensored variant
  • Low-bit quants reduce quality

At a glance

Type
Model
Runtime
GGUF / llama.cpp
Has code
no
License
Apache-2.0

Use cases and integrations

How curated lists describe it

Frequently asked questions

What is this?

GGUF quantizations of SargeDev/JEV-27B-VL-Uncensored with vision projector files.

Do I need the mmproj file?

Yes, for image input.

Is it official?

It is a community quantization of a community fine-tune, not a TypeSafe or AutoTrust release.

Related projects

  • Lichen★ 58

    Drop-in local replacement for Jev that serves /v1/systemone from open weights, including questions about images.

    ServicebetaPython
  • Jev Local

    Local /v1/systemone server in Japanese docs with LFM, Sarashina and fine-tuned ModernBERT-Ja backends, including image input.

    ServicebetaPython
  • NeoHorse-Jev-4B

    Hugging Face card for NeoHorse-Jev-4B: Apache-2.0 4B decision model for text or image-plus-text, served at /v1/systemone.

    ModelbetaPython
  • Standard One

    Standard Thinking's Apache-2.0 3B and 8B decision models on Ministral 3 that score bounded answers via /v1/systemone, with vision.

    ServicebetaPython
  • AutoJev

    Open 27B multimodal decision model built largely by autonomous agents, serving choice, noul and score on a TypeSafe-compatible API.

    ModelresearchPython
  • Winnow

    Apache-2.0 Gemma 4 12B fine-tune for local typed decisions, chat and image input, served via /v1/systemone and chat completions.

    Serviceresearch