CUSTOM
CLANKERS.
← Browse all models

lilcheaty / Model details

flint-abliterated-GGUF

lilcheaty/flint-abliterated-GGUF

abliteratedfine-tuned
Download files on Hugging Face ↗

Read the original model card ↗ · Choosing a model

Family: Unknown. No supported family evidence recorded.

About this model

lilcheaty's flint-abliterated-GGUF repository provides a GGUF quantization of a weight-edited derivative of RecursiveSI/flint. The creator describes the change as removing one estimated refusal direction from selected weights, applied shard by shard to the official BF16 weights, and states it is not an official Recursive release. The repository contains flint-abliterated-Q3_K_M.gguf, quantized to Q3_K_M from the edited BF16 checkpoint, under the Apache 2.0 license. According to the model card, in a small selected comparison the edited Q3_K_M model gave 0/20 explicit final-answer refusals on held-out refusal prompts and 0/20 refusals on normal coding prompts, with all 40 responses completed; the creator notes this is not a general safety, compliance or coding benchmark. The creator also says Flint GGUF requires llama.cpp PR #30928 until it merges.

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
RecursiveSI/flint
Parameters
Unknown
Main repository formats
GGUF
License tag
apache-2.0
Languages
Unknown
Last updated
2026-10-22 · 05:24:21.000 UTC

What changed

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

  • abliteratedsource tag: abliterated
  • abliteratedmodel name: flint-abliterated-GGUF
  • fine-tunedsource tag: base_model:finetune:RecursiveSI/flint

Family evidence

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

  • No supported family evidence recorded.

Available versions

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

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

Make a smaller download (quantize)

  • llama.cpp ↗ ★ 132,124

    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.

Learn the techniques

  • LLM Course ↗ ★ 84,633

    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
1,196
Likes
6
Metadata checked
2026-10-24 · 12:14:47 UTC
First seen in index
2026-10-24 · 12:14:47 UTC
Source revision
8866ae70d1726eee740c743bd6f94dbdee108e27

Source-card excerpt

Source model card excerpt: Flint abliterated Q3 K M This is a weight-edited derivative of RecursiveSI/flint, released under the same Apache 2.0 license. Recursive developed the base model.

From lilcheaty/flint-abliterated-GGUF. 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 run, host, redistribute, or test model weights.

Collection rules & limitations ↗