huihui

deepseek-r1-abliterated

DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.

606.7K Pulls 55 Tags Updated 6 months ago

qwen3-abliterated

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

tools thinking 0.6b 1.7b 4b 8b 14b 16b 30b 32b 235b

102.3K Pulls 74 Tags Updated 4 months ago

qwq-abliterated

QwQ is an experimental research model focused on advancing AI reasoning capabilities.

tools 32b

66.6K Pulls 17 Tags Updated 9 months ago

gemma3-abliterated

The current, most capable model that runs on a single GPU.

vision 270m 1b 4b 12b 27b

48.2K Pulls 16 Tags Updated 3 months ago

llama3.2-abliterate

Meta's Llama 3.2 goes small with 1B and 3B models.

tools 1b 3b

35K Pulls 11 Tags Updated 1 year ago

qwen2.5-1m-abliterated

Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens.

tools 7b 14b

32K Pulls 11 Tags Updated 10 months ago

llama3.3-abliterated

New state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model.

tools 70b

23.5K Pulls 10 Tags Updated 1 year ago

dolphin3-abliterated

Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.

tools 8b

22.9K Pulls 5 Tags Updated 11 months ago

qwen2.5-abliterate

Qwen2 is a new series of large language models from Alibaba group

tools 0.5b 1.5b 3b 7b 14b 32b 72b

22.7K Pulls 46 Tags Updated 7 months ago

qwen3-vl-abliterated

The most powerful vision-language model in the Qwen3 model family to date.

vision tools 2b 4b 8b 30b 32b

20.8K Pulls 54 Tags Updated 1 month ago

gpt-oss-abliterated

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.

tools thinking 20b 120b

16.9K Pulls 16 Tags Updated 2 months ago

gemma3n-abliterated

This is an uncensored version of google/gemma-3n created with abliteration

14.8K Pulls 2 Tags Updated 5 months ago

kimi-k2

This is not the ablation version. Kimi-K2-Instruct is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters.

tools 1026b

9,325 Pulls 4 Tags Updated 4 months ago

qwen2.5-coder-abliterate

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.

tools 0.5b 1.5b 3b 7b 14b 32b

9,258 Pulls 31 Tags Updated 1 year ago

phi4-abliterated

Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.

14b

8,346 Pulls 5 Tags Updated 11 months ago

deepseek-v3

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

7,125 Pulls 2 Tags Updated 10 months ago

mistral-small-abliterated

Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.

tools 24b

6,215 Pulls 10 Tags Updated 10 months ago

huihui-moe-abliterated

Huihui-MoE-abliterated is a **Mixture of Experts (MoE)** language model developed by **huihui.ai**

tools thinking 1.5b 5b 12b 23b 24b 46b 57b 60b

5,830 Pulls 40 Tags Updated 3 months ago

magistral-abliterated

This is an uncensored version of mistralai/magistral-Small-2506 created with abliteration

thinking 24b

5,050 Pulls 6 Tags Updated 6 months ago

granite3.2-vision-abliterated

A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.

vision tools 2b

5,039 Pulls 5 Tags Updated 9 months ago

hunyuan-mt-abliterated

The Hunyuan Translation Model comprises a translation model, Hunyuan-MT-7B, and an ensemble model, Hunyuan-MT-Chimera.

7b

4,778 Pulls 9 Tags Updated 3 months ago

phi4-mini-abliterated

Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.

tools 3.8b

4,077 Pulls 5 Tags Updated 9 months ago

qwen3-coder-abliterated

Qwen3-Coder featuring the following key enhancements: Significant Performance, Long-context Capabilities, Agentic Coding.

30b 480b

3,866 Pulls 9 Tags Updated 4 months ago

baronllm-abliterated

This is an uncensored version of AlicanKiraz0/BaronLLM_Offensive_Security_LLM_Q6_K_GGUF created with abliteration

tools 8b

3,721 Pulls 4 Tags Updated 6 months ago

deepseek-v3-abliterated

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

671b

2,823 Pulls 5 Tags Updated 8 months ago

openthinker-abliterated

A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.

7b 32b

2,662 Pulls 9 Tags Updated 10 months ago

qwenlong-abliterated

This is an uncensored version of Tongyi-Zhiwen/QwenLong-L1-32B created with abliteration

thinking 32b

2,238 Pulls 5 Tags Updated 6 months ago

deepseekr1-qwq-skyt1-fusion

`DeepSeekR1-QwQ-SkyT1-32B-Fusion` is a mixed model that combines the strengths of three powerful Qwen-based models: huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated, huihui-ai/QwQ-32B-Preview-abliterated and huihui-ai/Sky-T1-32B-Preview-abliterated

32b

2,068 Pulls 14 Tags Updated 9 months ago

deephermes3-abliterated

DeepHermes 3 Preview is the latest version of our flagship Hermes series of LLMs by Nous Research, and one of the first models in the world to unify Reasoning (long chains of thought that improve answer accuracy) and normal LLM response modes into one mod

8b

2,065 Pulls 6 Tags Updated 9 months ago

jan-nano-abliterated

This is an uncensored version of Menlo/Jan-nano created with abliteration

tools thinking 4b

1,999 Pulls 10 Tags Updated 5 months ago

aya-expanse-abliterated

Cohere For AI's language models trained to perform well across 23 different languages.

tools 8b 32b

1,933 Pulls 9 Tags Updated 1 year ago

tongyi-deepresearch-abliterated

tongyi DeepResearch, an agentic large language model featuring 30 billion total parameters, with only 3 billion activated per token.

tools thinking 30b

1,829 Pulls 5 Tags Updated 2 months ago

devstral-abliterated

This is an uncensored version of mistralai/Devstral-Small-2505 created with abliteration

tools 24b

1,798 Pulls 6 Tags Updated 6 months ago

exaone3.5-abliterated

EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.

2.4b 7.8b 32b

1,787 Pulls 13 Tags Updated 11 months ago

dolphin3-r1-abliterated

Dolphin's first generation reasoning models.

24b

1,699 Pulls 10 Tags Updated 10 months ago

skywork-o1-abliterated

The Skywork o1 Open model series, developed by the Skywork team at Kunlun Inc. This groundbreaking release introduces a series of models that incorporate o1-like slow thinking and reasoning capabilities.

tools 8b

1,655 Pulls 5 Tags Updated 1 year ago

granite3.2-abliterated

Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.

tools 2b 8b

1,639 Pulls 11 Tags Updated 9 months ago

am-thinking-abliterate

This is an uncensored version of a-m-team/AM-Thinking-v1 created with abliteration

tools 32b

1,600 Pulls 6 Tags Updated 7 months ago

acereason-nemotron-abliterated

This is an uncensored version of nvidia/AceReason-Nemotron created with abliteration Edit

7b 14b

1,549 Pulls 9 Tags Updated 6 months ago

arcee-blitz-abliterated

Arcee-Blitz (24B) is a new Mistral-based 24B model distilled from DeepSeek, designed to be both fast and efficient. We view it as a practical “workhorse” model that can tackle a range of tasks without the overhead of larger architectures.

24b

1,528 Pulls 5 Tags Updated 9 months ago

foundation-sec-abliterated

Foundation-Sec-8B-abliterated is an uncensored version fine-tuned based on fdtn-ai/Foundation-Sec-8B. Foundation-Sec-8B is an open-weight, 8-billion-parameter foundational language model designed specifically for cybersecurity applications.

8b

1,496 Pulls 5 Tags Updated 7 months ago

homunculus-abliterated

This is an uncensored version of arcee-ai/Homunculus created with abliteration

thinking 12b

1,454 Pulls 5 Tags Updated 6 months ago

exaone-deep-abliterated

This is an uncensored version of LGAI-EXAONE/EXAONE-Deep-2.4B created with abliteration

2.4b 7.8b

1,419 Pulls 9 Tags Updated 5 months ago

Hermes-3-Llama-3.2-abliterated

Hermes 3 3B is a small but mighty new addition to the Hermes series of LLMs by Nous Research, and is Nous's first fine-tune in this parameter class.

tools 3b

1,406 Pulls 5 Tags Updated 12 months ago

tess-r1-abliterated

Tess-R1 is designed with test-time compute in mind, and has the capabilities to produce a Chain-of-Thought (CoT) reasoning before producing the final output.

70b

1,354 Pulls 9 Tags Updated 9 months ago

tinyr1-abliterated

Tiny-R1-32B-Preview, which outperforms the 70B model Deepseek-R1-Distill-Llama-70B and nearly matches the full R1 model in math.

tools 32b

1,320 Pulls 6 Tags Updated 9 months ago

deepseek-v3-pruned

DeepSeek-V3-Pruned-Coder-411B is a pruned version of the DeepSeek-V3 reduced from 256 experts to 160 experts, The pruned model is mainly used for code generation.

411b

1,271 Pulls 5 Tags Updated 8 months ago

falcon3-abliterated

A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.

1b 3b 7b 10b

1,270 Pulls 21 Tags Updated 11 months ago

llama3.3-abliterated-ft

The fine-tuned version of huihui_ai/llama3.3-abliterated

tools 70b

1,243 Pulls 4 Tags Updated 11 months ago

phi4-reasoning-abliterated

Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.

3.8b

1,238 Pulls 4 Tags Updated 7 months ago

marco-o1-abliterated

An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).

7b

1,223 Pulls 5 Tags Updated 1 year ago

kanana-nano-abliterated

Kanana, a series of bilingual language models (developed by Kakao) that demonstrate exceeding performance in Korean and competitive performance in English.

2.1b

1,079 Pulls 5 Tags Updated 9 months ago

deepseek-r1-Fusion

DeepSeek-R1-Distill-Qwen-Coder-32B-Fusion-9010 is a mixed model that combines the strengths of two powerful DeepSeek-R1-Distill-Qwen-based models: huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated and huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated.

32b

1,034 Pulls 6 Tags Updated 9 months ago

deepscaler-abliterated

A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.

1.5b

1,020 Pulls 3 Tags Updated 10 months ago

fara-abliterated

Fara-7B is Microsoft's first agentic small language model (SLM) designed specifically for computer use.

vision 7b

967 Pulls 5 Tags Updated 2 weeks ago

qwq-fusion

qwq-fusion is a mixed model that combines the strengths of two powerful Qwen-based models: huihui-ai/QwQ-32B-Preview-abliterated and huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated.

tools 32b

896 Pulls 14 Tags Updated 1 year ago

internlm3-abliterated

InternLM3 has open-sourced an 8-billion parameter instruction model, InternLM3-8B-Instruct, designed for general-purpose usage and advanced reasoning.

8b

872 Pulls 5 Tags Updated 11 months ago

granite3.1-dense-abliterated

The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.

tools 2b 8b

861 Pulls 11 Tags Updated 11 months ago

perplexity-ai-r1-abliterated

A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.

70b

849 Pulls 10 Tags Updated 9 months ago

qwen2.5-vl-abliterated

Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.

vision 3b 7b 32b

803 Pulls 16 Tags Updated 1 month ago

seed-coder-abliterate

This is an uncensored version of ByteDance-Seed/Seed-Coder-8B-Instruct created with abliteration

753 Pulls 5 Tags Updated 7 months ago

command-r7b-abliterated

he smallest model in Cohere's R series delivers top-tier speed, efficiency, and quality to build powerful AI applications on commodity GPUs and edge devices.

tools 7b

693 Pulls 5 Tags Updated 11 months ago

smallthinker-abliterated

A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.

3b

684 Pulls 5 Tags Updated 11 months ago

qwen3-next-abliterated

The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.

tools thinking 80b

647 Pulls 10 Tags Updated 3 days ago

mirothinker1-abliterated

MiroThinker v1.0 is an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities.

tools thinking 8b 30b 72b

644 Pulls 18 Tags Updated 2 weeks ago

tulu3-abliterate

Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.

8b 70b

623 Pulls 9 Tags Updated 1 year ago

nemotron-v1-abliterated

Llama Nemotron, Open, Production-ready Enterprise Models

tools 8b

616 Pulls 6 Tags Updated 7 months ago

Qwen3-Coder

This is not the ablation version. Qwen3-Coder featuring the following key enhancements: Significant Performance, Long-context Capabilities, Agentic Coding.

tools thinking 480b

610 Pulls 4 Tags Updated 4 months ago

microthinker

MicroThinker is an experimental research model focused on advancing AI reasoning capabilities.

tools 1b 3b 8b

566 Pulls 12 Tags Updated 10 months ago

openhands-lm-abliterated

OpenHands LM is built on the foundation of Qwen Coder 2.5 Instruct 32B, leveraging its powerful base capabilities for coding tasks.

tools 32b

561 Pulls 7 Tags Updated 8 months ago

huihui-moe

Huihui-MoE is a Mixture of Experts (MoE) language model developed by huihui.ai

tools thinking 1.2b 23b

547 Pulls 10 Tags Updated 5 months ago

nemotron-abliterated

Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.

tools 70b

439 Pulls 6 Tags Updated 11 months ago

perplexity-ai-r1

A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.

426 Pulls 2 Tags Updated 9 months ago

s1.1-abliterated

This model is a successor of s1-32B with slightly better performance.

tools 32b

360 Pulls 4 Tags Updated 10 months ago

s1-abliterated

s1 is a reasoning model finetuned from Qwen2.5-32B-Instruct on just 1,000 examples. It matches o1-preview & exhibits test-time scaling via budget forcing.

tools 32b

326 Pulls 9 Tags Updated 10 months ago

orchestrator-abliterated

Orchestrator-8B is a state-of-the-art 8B parameter orchestration model designed to solve complex, multi-turn agentic tasks by coordinating a diverse set of expert models and tools.

tools thinking 8b

315 Pulls 5 Tags Updated 1 week ago

uwu-abliterated

UwU is an experimental research model focused on advancing AI reasoning capabilities.

7b

295 Pulls 5 Tags Updated 11 months ago

Lucie-abliterated

Lucie-7B is a pretrained 7B parameter causal language model built by LINAGORA and OpenLLM-France.

7b

286 Pulls 5 Tags Updated 11 months ago

fluentlylm-prinum-abliterated

fluently-lm/FluentlyLM-Prinum

tools 32b

225 Pulls 5 Tags Updated 9 months ago

skyt1-abliterated

Sky-T1-32B-Preview is an experimental research model focused on advancing AI reasoning capabilities

tools 32b

197 Pulls 5 Tags Updated 10 months ago

deepseek-r1

DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen.

thinking 671b

173 Pulls 12 Tags Updated 6 months ago

megrez-abliterated

Megrez-3B aims to provide a fast inference, compact, and powerful edge-side intelligent solution through software-hardware co-design.

tools 7b

147 Pulls 6 Tags Updated 11 months ago

glm4.6-abliterated

Advanced agentic, reasoning and coding capabilities.

tools thinking 357b

126 Pulls 4 Tags Updated 1 week ago

qwen2.5-censortune

CensorTune with Supervised Fine-Tuning (SFT) to fine-tune the Qwen2.5-Instruct model on 622 harmful instructions in a single fine-tuning iteration, achieving rejection of these instructions and a zero-pass rate for 320

tools 0.5b 1.5b 3b

126 Pulls 15 Tags Updated 7 months ago

deepseek-v3.1

This is not the ablation version. DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode.

tools thinking 671b

88 Pulls 3 Tags Updated 3 months ago

deepseek-r1-pruned

DeepSeek-R1-Pruned-Coder-411B is a pruned version of the DeepSeek-R1 reduced from 256 experts to 160 experts, The pruned model is mainly used for code generation.

411b

76 Pulls 3 Tags Updated 9 months ago

kimi-k2-abliterated

A state-of-the-art mixture-of-experts (MoE) language model. Kimi K2-Instruct-0905 demonstrates significant improvements in performance on public benchmarks and real-world coding agent tasks.

tools 1026b

20 Pulls 3 Tags Updated 3 days ago

support@huihui.ai

deepseek-r1-abliterated

qwen3-abliterated

qwq-abliterated

gemma3-abliterated

llama3.2-abliterate

qwen2.5-1m-abliterated

llama3.3-abliterated

dolphin3-abliterated

qwen2.5-abliterate

qwen3-vl-abliterated

gpt-oss-abliterated

gemma3n-abliterated

kimi-k2

qwen2.5-coder-abliterate

phi4-abliterated

deepseek-v3

mistral-small-abliterated

huihui-moe-abliterated

magistral-abliterated

granite3.2-vision-abliterated

hunyuan-mt-abliterated

phi4-mini-abliterated

qwen3-coder-abliterated

baronllm-abliterated

deepseek-v3-abliterated

openthinker-abliterated

qwenlong-abliterated

deepseekr1-qwq-skyt1-fusion

deephermes3-abliterated

jan-nano-abliterated

aya-expanse-abliterated

tongyi-deepresearch-abliterated

devstral-abliterated

exaone3.5-abliterated

dolphin3-r1-abliterated

skywork-o1-abliterated

granite3.2-abliterated

am-thinking-abliterate

acereason-nemotron-abliterated

arcee-blitz-abliterated

foundation-sec-abliterated

homunculus-abliterated

exaone-deep-abliterated

Hermes-3-Llama-3.2-abliterated

tess-r1-abliterated

tinyr1-abliterated

deepseek-v3-pruned

falcon3-abliterated

llama3.3-abliterated-ft

phi4-reasoning-abliterated

marco-o1-abliterated

kanana-nano-abliterated

deepseek-r1-Fusion

deepscaler-abliterated

fara-abliterated

qwq-fusion

internlm3-abliterated

granite3.1-dense-abliterated

perplexity-ai-r1-abliterated

qwen2.5-vl-abliterated

seed-coder-abliterate

command-r7b-abliterated

smallthinker-abliterated

qwen3-next-abliterated

mirothinker1-abliterated

tulu3-abliterate

nemotron-v1-abliterated

Qwen3-Coder

microthinker

openhands-lm-abliterated

huihui-moe

nemotron-abliterated

perplexity-ai-r1

s1.1-abliterated

s1-abliterated

orchestrator-abliterated

uwu-abliterated

Lucie-abliterated

fluentlylm-prinum-abliterated