support@huihui.ai
-
deepseek-r1-abliterated
DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.
7b 8b 14b 32b 70b435.6K Pulls 46 Tags Updated 7 weeks ago
-
qwq-abliterated
QwQ is an experimental research model focused on advancing AI reasoning capabilities.
tools 32b55.8K Pulls 17 Tags Updated 2 weeks ago
-
llama3.2-abliterate
Meta's Llama 3.2 goes small with 1B and 3B models.
tools 1b 3b29.7K Pulls 11 Tags Updated 4 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 14b18.2K Pulls 11 Tags Updated 8 weeks 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 72b12K Pulls 36 Tags Updated 3 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 32b5,016 Pulls 31 Tags Updated 4 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 70b3,426 Pulls 10 Tags Updated 3 months ago
-
phi4-abliterated
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
14b3,011 Pulls 5 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.
2,381 Pulls 2 Tags Updated 2 months ago
-
mistral-small-abliterated
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
tools 24b1,984 Pulls 10 Tags Updated 7 weeks 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
32b1,443 Pulls 14 Tags Updated 4 weeks ago
-
gemma3-abliterated
The current, most capable model that runs on a single GPU.
vision 1b 4b 12b1,294 Pulls 11 Tags Updated yesterday
-
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 8b1,268 Pulls 5 Tags Updated 3 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 8b1,114 Pulls 5 Tags Updated 2 months ago
-
marco-o1-abliterated
An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).
7b1,081 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 32b1,071 Pulls 9 Tags Updated 3 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.
70b912 Pulls 9 Tags Updated 4 weeks ago
-
openthinker-abliterated
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
7b 32b901 Pulls 9 Tags Updated 5 weeks ago
-
dolphin3-r1-abliterated
Dolphin's first generation reasoning models.
24b839 Pulls 10 Tags Updated 6 weeks 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 32b838 Pulls 6 Tags Updated 3 weeks 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 10b780 Pulls 21 Tags Updated 3 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 32b709 Pulls 13 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 3.8b706 Pulls 5 Tags Updated 3 weeks ago
-
internlm3-abliterated
InternLM3 has open-sourced an 8-billion parameter instruction model, InternLM3-8B-Instruct, designed for general-purpose usage and advanced reasoning.
8b699 Pulls 5 Tags Updated 2 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
8b671 Pulls 6 Tags Updated 4 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 32b641 Pulls 14 Tags Updated 3 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 8b583 Pulls 11 Tags Updated 3 months ago
-
llama3.3-abliterated-ft
The fine-tuned version of huihui_ai/llama3.3-abliterated
tools 70b559 Pulls 4 Tags Updated 3 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 2b545 Pulls 5 Tags Updated 2 weeks 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 3b517 Pulls 5 Tags Updated 3 months ago
-
smallthinker-abliterated
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
3b466 Pulls 5 Tags Updated 2 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 8b422 Pulls 11 Tags Updated 2 weeks 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 7b410 Pulls 5 Tags Updated 2 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.
70b402 Pulls 10 Tags Updated 3 weeks 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.
32b399 Pulls 6 Tags Updated 4 weeks 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.
1.5b392 Pulls 3 Tags Updated 5 weeks ago
-
microthinker
MicroThinker is an experimental research model focused on advancing AI reasoning capabilities.
tools 1b 3b 8b390 Pulls 12 Tags Updated 8 weeks 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.
24b387 Pulls 5 Tags Updated 3 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 70b344 Pulls 9 Tags Updated 3 months ago
-
s1.1-abliterated
This model is a successor of s1-32B with slightly better performance.
tools 32b300 Pulls 4 Tags Updated 5 weeks 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.
2.1b284 Pulls 5 Tags Updated 3 weeks 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 32b262 Pulls 9 Tags Updated 5 weeks 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 70b242 Pulls 6 Tags Updated 3 months ago
-
uwu-abliterated
UwU is an experimental research model focused on advancing AI reasoning capabilities.
7b214 Pulls 5 Tags Updated 2 months ago
-
skyt1-abliterated
Sky-T1-32B-Preview is an experimental research model focused on advancing AI reasoning capabilities
tools 32b154 Pulls 5 Tags Updated 2 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.
148 Pulls 2 Tags Updated 4 weeks ago
-
Lucie-abliterated
Lucie-7B is a pretrained 7B parameter causal language model built by LINAGORA and OpenLLM-France.
7b138 Pulls 5 Tags Updated 2 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 7b96 Pulls 6 Tags Updated 2 months ago
-
fluentlylm-prinum-abliterated
fluently-lm/FluentlyLM-Prinum
tools 32b83 Pulls 5 Tags Updated 3 weeks 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.
671b54 Pulls 3 Tags Updated 5 weeks 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.
411b41 Pulls 3 Tags Updated 12 days 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.
411b10 Pulls 3 Tags Updated 6 days ago