
support@huihui.ai
-
deepseek-r1-abliterated
DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.
thinking 1.5b 7b 8b 14b 32b 70b570.4K Pulls 55 Tags Updated 4 months ago
-
qwq-abliterated
QwQ is an experimental research model focused on advancing AI reasoning capabilities.
tools 32b64.9K Pulls 17 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 235b60.3K Pulls 74 Tags Updated 1 month ago
-
gemma3-abliterated
The current, most capable model that runs on a single GPU.
270m 1b 4b 12b 27b35.3K Pulls 16 Tags Updated 1 month ago
-
llama3.2-abliterate
Meta's Llama 3.2 goes small with 1B and 3B models.
tools 1b 3b33.7K Pulls 11 Tags Updated 10 months 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 14b30.4K Pulls 11 Tags Updated 8 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 70b22K Pulls 10 Tags Updated 9 months 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 8b21K Pulls 5 Tags Updated 8 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 72b19.5K Pulls 46 Tags Updated 5 months ago
-
gemma3n-abliterated
This is an uncensored version of google/gemma-3n created with abliteration
12.7K Pulls 2 Tags Updated 2 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 32b8,412 Pulls 31 Tags Updated 10 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 1026b8,360 Pulls 4 Tags Updated 2 months ago
-
deepseek-v3
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
7,099 Pulls 2 Tags Updated 8 months ago
-
phi4-abliterated
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
14b7,048 Pulls 5 Tags Updated 8 months ago
-
gpt-oss-abliterated
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
tools thinking 20b 120b6,328 Pulls 16 Tags Updated yesterday
-
mistral-small-abliterated
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
tools 24b5,286 Pulls 10 Tags Updated 7 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 2b4,360 Pulls 5 Tags Updated 6 months ago
-
magistral-abliterated
This is an uncensored version of mistralai/magistral-Small-2506 created with abliteration
thinking 24b4,181 Pulls 6 Tags Updated 3 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 60b4,156 Pulls 40 Tags Updated 2 weeks 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 3.8b3,660 Pulls 5 Tags Updated 7 months ago
-
baronllm-abliterated
This is an uncensored version of AlicanKiraz0/BaronLLM_Offensive_Security_LLM_Q6_K_GGUF created with abliteration
tools 8b2,817 Pulls 4 Tags Updated 3 months ago
-
qwen3-coder-abliterated
Qwen3-Coder featuring the following key enhancements: Significant Performance, Long-context Capabilities, Agentic Coding.
30b 480b2,374 Pulls 9 Tags Updated 1 month ago
-
hunyuan-mt-abliterated
The Hunyuan Translation Model comprises a translation model, Hunyuan-MT-7B, and an ensemble model, Hunyuan-MT-Chimera.
7b2,367 Pulls 9 Tags Updated 3 weeks ago
-
deepseek-v3-abliterated
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
671b2,092 Pulls 5 Tags Updated 5 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
32b1,999 Pulls 14 Tags Updated 7 months ago
-
qwenlong-abliterated
This is an uncensored version of Tongyi-Zhiwen/QwenLong-L1-32B created with abliteration
thinking 32b1,823 Pulls 5 Tags Updated 4 months ago
-
aya-expanse-abliterated
Cohere For AI's language models trained to perform well across 23 different languages.
tools 8b 32b1,766 Pulls 9 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
8b1,744 Pulls 6 Tags Updated 7 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 32b1,686 Pulls 13 Tags Updated 9 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 8b1,606 Pulls 5 Tags Updated 10 months ago
-
dolphin3-r1-abliterated
Dolphin's first generation reasoning models.
24b1,503 Pulls 10 Tags Updated 7 months 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 8b1,458 Pulls 11 Tags Updated 6 months ago
-
jan-nano-abliterated
This is an uncensored version of Menlo/Jan-nano created with abliteration
tools thinking 4b1,456 Pulls 10 Tags Updated 2 months ago
-
acereason-nemotron-abliterated
This is an uncensored version of nvidia/AceReason-Nemotron created with abliteration Edit
7b 14b1,380 Pulls 9 Tags Updated 4 months ago
-
openthinker-abliterated
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
7b 32b1,370 Pulls 9 Tags Updated 7 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.
411b1,251 Pulls 5 Tags Updated 6 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 32b1,246 Pulls 6 Tags Updated 7 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.
24b1,211 Pulls 5 Tags Updated 7 months ago
-
exaone-deep-abliterated
This is an uncensored version of LGAI-EXAONE/EXAONE-Deep-2.4B created with abliteration
2.4b 7.8b1,199 Pulls 9 Tags Updated 3 months ago
-
marco-o1-abliterated
An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).
7b1,190 Pulls 5 Tags Updated 10 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.
8b1,182 Pulls 5 Tags Updated 4 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 3b1,181 Pulls 5 Tags Updated 9 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 10b1,181 Pulls 21 Tags Updated 9 months ago
-
devstral-abliterated
This is an uncensored version of mistralai/Devstral-Small-2505 created with abliteration
tools 24b1,123 Pulls 6 Tags Updated 4 months ago
-
am-thinking-abliterate
This is an uncensored version of a-m-team/AM-Thinking-v1 created with abliteration
tools 32b1,107 Pulls 6 Tags Updated 4 months ago
-
llama3.3-abliterated-ft
The fine-tuned version of huihui_ai/llama3.3-abliterated
tools 70b1,065 Pulls 4 Tags Updated 9 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.
70b955 Pulls 9 Tags Updated 7 months 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.
2.1b948 Pulls 5 Tags Updated 7 months ago
-
homunculus-abliterated
This is an uncensored version of arcee-ai/Homunculus created with abliteration
thinking 12b899 Pulls 5 Tags Updated 3 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.
1.5b856 Pulls 3 Tags Updated 7 months 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 32b856 Pulls 14 Tags Updated 10 months ago
-
internlm3-abliterated
InternLM3 has open-sourced an 8-billion parameter instruction model, InternLM3-8B-Instruct, designed for general-purpose usage and advanced reasoning.
8b846 Pulls 5 Tags Updated 8 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 8b788 Pulls 11 Tags Updated 9 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.
70b766 Pulls 10 Tags Updated 7 months ago
-
phi4-reasoning-abliterated
Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.
3.8b717 Pulls 4 Tags Updated 4 months ago
-
tongyi-deepresearch-abliterated
ongyi DeepResearch, an agentic large language model featuring 30 billion total parameters, with only 3 billion activated per token.
tools thinking 30b692 Pulls 5 Tags Updated 1 week 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 7b655 Pulls 5 Tags Updated 8 months ago
-
smallthinker-abliterated
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
3b632 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.
32b618 Pulls 6 Tags Updated 7 months ago
-
seed-coder-abliterate
This is an uncensored version of ByteDance-Seed/Seed-Coder-8B-Instruct created with abliteration
616 Pulls 5 Tags Updated 4 months 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 70b594 Pulls 9 Tags Updated 10 months ago
-
nemotron-v1-abliterated
Llama Nemotron, Open, Production-ready Enterprise Models
tools 8b561 Pulls 6 Tags Updated 5 months ago
-
microthinker
MicroThinker is an experimental research model focused on advancing AI reasoning capabilities.
tools 1b 3b 8b538 Pulls 12 Tags Updated 8 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 480b501 Pulls 4 Tags Updated 2 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 32b479 Pulls 7 Tags Updated 5 months ago
-
huihui-moe
Huihui-MoE is a Mixture of Experts (MoE) language model developed by huihui.ai
tools thinking 1.2b 23b419 Pulls 10 Tags Updated 3 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 70b401 Pulls 6 Tags Updated 9 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.
384 Pulls 2 Tags Updated 7 months ago
-
s1.1-abliterated
This model is a successor of s1-32B with slightly better performance.
tools 32b345 Pulls 4 Tags Updated 7 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 32b320 Pulls 9 Tags Updated 7 months ago
-
uwu-abliterated
UwU is an experimental research model focused on advancing AI reasoning capabilities.
7b280 Pulls 5 Tags Updated 8 months ago
-
Lucie-abliterated
Lucie-7B is a pretrained 7B parameter causal language model built by LINAGORA and OpenLLM-France.
7b261 Pulls 5 Tags Updated 8 months ago
-
fluentlylm-prinum-abliterated
fluently-lm/FluentlyLM-Prinum
tools 32b216 Pulls 5 Tags Updated 7 months ago
-
skyt1-abliterated
Sky-T1-32B-Preview is an experimental research model focused on advancing AI reasoning capabilities
tools 32b189 Pulls 5 Tags Updated 8 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 671b156 Pulls 12 Tags Updated 3 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 7b144 Pulls 6 Tags Updated 8 months 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 3b98 Pulls 15 Tags Updated 5 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.
411b76 Pulls 3 Tags Updated 6 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 671b44 Pulls 3 Tags Updated 1 month ago