richardyoung

qwen3-14b-abliterated

Abliterated Qwen3-14B with 80% reduced refusals while preserving coherence (KL 0.98)

14.2K Pulls 6 Tags Updated 7 months ago

qwythos-9b-abliterated

Abliterated build of Qwythos-9B-Claude-Mythos, a Claude-style creative & reasoning model (Qwen3.5-9B base) with refusals further reduced via the Heretic library.

12.3K Pulls 6 Tags Updated 1 month ago

deepseek-r1-32b-uncensored

Advanced reasoning model with uncensored capabilities, perfect for complex problem-solving and unrestricted conversations without refusal behavior

8,365 Pulls 1 Tag Updated 8 months ago

olmocr2

State-of-the-art OCR (Optical Character Recognition) vision language model based on [allenai/olmOCR-2-7B-1025](https://huggingface.co/allenai/olmOCR-2-7B-1025).

vision

7,250 Pulls 1 Tag Updated 9 months ago

qwen3.6-27b-abliterated

Abliterated (uncensored) version of **Qwen/Qwen3.6-27B**, refusal behavior reduced via targeted weight modification with the Heretic library, while preserving coherence.

4,153 Pulls 6 Tags Updated 1 month ago

qwen2.5-7b-instruct-abliterated

An abliterated (uncensored) build of Qwen2.5-7B-Instruct with reduced refusal behavior and preserved general capability.

2,369 Pulls 4 Tags Updated 1 month ago

smolvlm2-2.2b-instruct

SmolVLM2-2.2B-Instruct is a lightweight yet powerful vision-language model that can understand images, read documents, and analyze video frames. At just 2.2B parameters, it runs efficiently on consumer hardware including laptops and smartphones, making

2,363 Pulls 7 Tags Updated 8 months ago

qwen3-coder

The most powerful open-source coding AI - 480B parameters with Mixture of Experts architecture for exceptional code generation and understanding.

2,355 Pulls 8 Tags Updated 8 months ago

qwen2.5-14b-1m-heretic

Ultra long-context model supporting 1M tokens with uncensored outputs, ideal for analyzing entire books, codebases, and extensive documents.

1,953 Pulls 1 Tag Updated 8 months ago

qwen2.5-14b-instruct-abliterated

Uncensored, abliterated build of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct), Alibaba's capable 14B instruct model

1,836 Pulls 2 Tags Updated 1 month ago

llama-3.2-3b-instruct-abliterated

Uncensored, abliterated build of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct), Meta's compact instruct model with safety refusals surgically removed via [Heretic](https://github.com/p-e-w/heretic).

1,361 Pulls 2 Tags Updated 1 month ago

kimi-vl-a3b-thinking

Kimi-VL-A3B-Thinking is a powerful vision-language model from Moonshot AI featuring extended thinking capabilities. Built on the DeepSeek2 architecture with Mixture of Experts (MoE), it excels at complex visual reasoning tasks, mathematical problem-s

1,266 Pulls 7 Tags Updated 8 months ago

qwen2.5-coder-14b-instruct-abliterated

Uncensored, abliterated build of [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct), Alibaba's flagship 14B coding model

1,263 Pulls 2 Tags Updated 1 month ago

qwen3.6-27b-code-abliterated

Code-safety abliterated build of Qwen/Qwen3.6-27B, refusals on malicious-code requests reduced via a *code-specific* refusal-direction ablation, while preserving coherence.

1,184 Pulls 5 Tags Updated 1 month ago

qwen3-8b-abliterated

Abliterated (uncensored) version of Qwen3-8B for unrestricted conversations, reasoning, and creative writing.

1,060 Pulls 1 Tag Updated 7 months ago

qwable-9b-abliterated

Abliterated build of Qwable-9B-Claude-Fable, a Claude-style creative and reasoning model (Qwen3.5-9B base) with refusals reduced via the Heretic library.

1,034 Pulls 6 Tags Updated 1 month ago

deepseek-coder-33b-heretic

State-of-the-art coding AI trained on 2T tokens with project-level understanding and no content restrictions for unrestricted code generation.

919 Pulls 1 Tag Updated 8 months ago

qwen2.5-3b-instruct-abliterated

Uncensored, abliterated build of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct), Alibaba's compact instruct model

897 Pulls 2 Tags Updated 1 month ago

gemma-4-12b-coder-abliterated

a Gemma-4 12B coding model with refusals dramatically reduced via the Heretic library.

tools thinking

851 Pulls 6 Tags Updated 1 month ago

qwen3-4b-instruct-2507-abliterated

Uncensored, abliterated build of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507), Alibaba's 4B non-thinking instruct model

784 Pulls 2 Tags Updated 1 month ago

llama-3.1-8b-instruct-abliterated

An uncensored, abliterated build of Meta's **Llama 3.1 8B Instruct**. Abliteration surgically removes the model's learned refusal direction while preserving its general capabilities

754 Pulls 2 Tags Updated 1 month ago

dolphin-yi-34b-heretic

Exceptional conversational AI with 77.4 MMLU score, offering natural dialogue and multi-domain expertise without any content filtering.

722 Pulls 1 Tag Updated 8 months ago

mistral-7b-instruct-v0.3-abliterated

A conservatively abliterated Mistral-7B-Instruct-v0.3 with reduced refusals, an extended 32K vocabulary, function calling, and preserved instruction-following quality.

694 Pulls 1 Tag Updated 7 months ago

uigen-x-30b-moe

Unsloth-tuned Qwen3 30B mixture‑of‑experts model built for heavy coding, reasoning, and agentic workflows.

529 Pulls 6 Tags Updated 10 months ago

gemma-2-9b-it-abliterated

Abliterated (uncensored) version of Gemma 2 9B Instruct for unrestricted conversations and creative writing.

405 Pulls 1 Tag Updated 7 months ago

kat-dev-72b

A 72B parameter coding model optimized for software engineering tasks, based on the Qwen2.5-72B architecture.

273 Pulls 6 Tags Updated 9 months ago

gpt-oss-20b-abliterated

Abliterated build of OpenAI gpt-oss-20b. Note up front: gpt-oss is highly refusal-robust, so this is a modest reduction, published honestly.

260 Pulls 2 Tags Updated 1 month ago

olmo-3-7b-rlzero-math

A 7B math reasoning model from Allen AI, trained with RL-Zero to solve problems step-by-step like a skilled tutor. Supports 65K context for complex multi-step problems - runs on any laptop.

242 Pulls 7 Tags Updated 8 months ago

gemma-7b-it-abliterated

Abliterated (uncensored) version of Gemma-7B-IT for unrestricted conversations and creative writing

159 Pulls 1 Tag Updated 7 months ago

qwen3-32b

Revolutionary model with unique thinking/non-thinking modes, delivering superior reasoning performance with seamless mode switching for any task.

156 Pulls 1 Tag Updated 8 months ago

schematron-3b

Schematron-3B is a 3.2B-parameter Llama-architecture chat model (inference-net/Schematron-3B) converted to GGUF for llama.cpp/Ollama, with two published quantizations: Q4_K_M (recommended balance) and IQ4_XS (smaller). It supports up to 131,072 context

136 Pulls 2 Tags Updated 7 months ago

mythos-9b-unhinged-abliterated

131 Pulls 1 Tag Updated 1 month ago

schematron-8b

Schematron-8B is an ~8B-parameter, Llama-architecture instruction model (inference-net/Schematron-8B) packaged for Ollama with long-context metadata (131K) and two GGUF quantizations: Q4_K_M (recommended) and IQ4_XS (smaller/faster).

123 Pulls 2 Tags Updated 7 months ago

openbiollm

122 Pulls 1 Tag Updated 2 years ago

calme-3.2

Calme 3.2 Instruct 78B - GGUF Q8_0 quantization of MaziyarPanahi's powerful Qwen2.5-based model

121 Pulls 1 Tag Updated 1 year ago

fable-qwen2.5-3b-abliterated

91 Pulls 1 Tag Updated 1 month ago

qwen3-4b-reasoning

qwen3-4b-reasoning is a 4B-parameter Qwen3-based reasoning “backfill” fine-tune (joeyzero/Qwen3-4B-Reasoning-Backfill-v0.1) converted to GGUF for llama.cpp/Ollama, with ~40K context and published as Q4_K_M (recommended) and iq4_xs (smaller).

88 Pulls 2 Tags Updated 7 months ago

bfs-prover-v2-32b

ByteDance Seed’s BFS-Prover-V2 is a 32B Qwen2.5-based Lean4 tactic generator trained with multi-turn off-policy RL plus multi-agent best-first search on Mathlib, Lean GitHub, and NuminaMath.

86 Pulls 3 Tags Updated 10 months ago

mythos-qwen-1.5b-abliterated

80 Pulls 1 Tag Updated 1 month ago

stablelm-2-12b-chat-abliterated

This is an abliterated version of [stabilityai/stablelm-2-12b-chat](https://huggingface.co/stabilityai/stablelm-2-12b-chat) that reduces refusal behavior through targeted weight modification.

79 Pulls 1 Tag Updated 7 months ago

llama-medx_v32

https://huggingface.co/skumar9/Llama-medx_v3.2

tools

71 Pulls 1 Tag Updated 1 year ago

mythos-9b-merged-abliterated

53 Pulls 1 Tag Updated 1 month ago

mythos-nano-abliterated

47 Pulls 1 Tag Updated 1 month ago

zephyr-7b-beta-abliterated

An abliterated build of HuggingFaceH4's Zephyr-7B-β

44 Pulls 1 Tag Updated 7 months ago

sensenova-si-2b

sensenova-si-2b is a ~2B-parameter Qwen2-architecture model from sensenova/sensenova-si (built on OpenGVLab’s InternVL3‑2B) converted to GGUF for llama.cpp/Ollama, with 32K context and two published quants: Q4_K_M (recommended) and iq4_xs (smaller).

22 Pulls 2 Tags Updated 7 months ago

nomos-1

A 30B-parameter (Mixture-of-Experts) model specialized for **mathematical problem-solving and proof-writing in natural language**, packaged for Ollama with a 256K context window.

14 Pulls 2 Tags Updated 7 months ago

https://deepneuro.ai/richard