CUSTOM
CLANKERS.
← Browse all models

allura-org / Model details

Q3-8B-Kintsugi

allura-org/Q3-8B-Kintsugi

fine-tuned
Download files on Hugging Face ↗

Read the original model card ↗ · Choosing a model

About this model

allura-org's Q3-8B-Kintsugi is a roleplaying model derived from Qwen/Qwen3-8B-Base and released as safetensors weights under an Apache-2.0 license. According to the model card, the base model first went through supervised fine-tuning on instruction-following data, roleplay conversations, and human writing from the Ink, Bigger Body, and Remnant lineage, followed by a KTO reinforcement-learning phase intended to reduce overly purple prose and improve logical and spatial reasoning. The creator says the official instruction-following Qwen3-8B was not used as the base, instruction-following was trained post-hoc, and thinking traces were not included, so 'thinking' will not function. The card states that during testing Kintsugi punched above its weight class for one-on-one roleplaying and general storywriting, but this has not been independently verified here. The repository is tagged as fine-tuned and lists safetensors as the weight format.

Description sources

Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.

Size and formats

Base model
Qwen/Qwen3-8B-Base
Parameters
8.19074B
Main repository formats
safetensors
License tag
apache-2.0
Languages
Unknown
Last updated
2025-09-03 · 00:15:30.000 UTC

What changed

Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.

  • fine-tunedsource tag: base_model:finetune:Qwen/Qwen3-8B-Base

Family evidence

These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.

  • Qwen: Base model: Qwen/Qwen3-8B-Base

Available versions

Versions appear here only when they explicitly name this exact model as their source. Check each repository for available files.

Link to this listing

Made or quantized this model? Paste one of these into your model card or README so people can find this listing.

Markdown

[Listed on Custom Clankers](https://customclankers.com/models/allura-org-q3-8b-kintsugi/)

HTML

<a href="https://customclankers.com/models/allura-org-q3-8b-kintsugi/">Listed on Custom Clankers</a>

Plain text links only: no image, no script, nothing loaded from this site.

Customize or build on this model

Listed from public GitHub data, not tested by us. Read the code and license before you run anything.

Tools to customize it further

Remove more refusals

  • Heretic ↗ ★ 36,457

    Removes refusal behavior from transformer models automatically. It pairs directional ablation (abliteration) with an Optuna parameter search that tries to cut refusals while keeping the model close to the original, so you don't have to pick layers by hand.

  • OBLITERATUS ↗ ★ 8,949

    A larger refusal-removal toolkit with several abliteration methods, usable locally or through a hosted Hugging Face Space. Check the telemetry setting before you run it: the README describes telemetry as opt-in, but on by default in the Spaces version.

Fine-tune it on your own data

  • Unsloth ↗ ★ 78,549

    A desktop app and Python library for running and training models locally. Its README lists LoRA, QLoRA, full fine-tuning, DPO and GRPO, plus export to formats including GGUF, on Windows, Linux, WSL and macOS.

  • LlamaFactory ↗ ★ 75,720

    Fine-tunes more than 100 language and vision-language models from a command line or a browser-based Web UI, aimed at training without writing code.

Make a smaller download (quantize)

  • llama.cpp ↗ ★ 132,313

    Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.

  • MLX LM ↗ ★ 7,470

    Apple's MLX package for running and fine-tuning models on Apple silicon. It can quantize models and upload them to the Hugging Face Hub, and supports LoRA and full fine-tuning.

Merge it with another model

  • mergekit ↗ ★ 7,415

    Merges pretrained models with many merge methods. It works out-of-core, so merges can run on a CPU or with as little as 8 GB of VRAM, and it also handles LoRA extraction and mixture-of-experts merges.

Learn the techniques

  • LLM Course ↗ ★ 84,684

    A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.

Compare all tools →

Source provenance

Downloads
33
Likes
6
Metadata checked
2026-10-26 · 00:11:46 UTC
First seen in index
2026-10-26 · 00:11:46 UTC
Source revision
c99f68c5b7dc071815aead1feadce0b9a96a797b

Source-card excerpt

Source model card excerpt: Q3-8B-Kintsugi get it? because kintsugi sounds like kitsune? hahaha- Overview Q3-8B-Kintsugi is a roleplaying model finetuned from Qwen3-8B-Base. During testing, Kintsugi punched well above

From allura-org/Q3-8B-Kintsugi. Creator model-card excerpt, not an independent review.

Inspect before you run

Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.

This directory does not host or redistribute model weights. Refusal profiles are measured by us on a fixed prompt set; all other behavior claims are source-reported.

Collection rules & limitations ↗