-
deepseek-r1-abliterated
DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.
thinking 1.5b 7b 8b 14b 32b 70b673.6K Pulls 55 Tags Updated 10 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 235b175.6K Pulls 74 Tags Updated 8 months ago
-
qwen3.5-abliterated
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
vision tools thinking 0.8b 2b 4b 9b 27b 35b 122b137.8K Pulls 58 Tags Updated 1 week ago
-
gemma3-abliterated
The current, most capable model that runs on a single GPU.
vision 270m 1b 4b 12b 27b79.5K Pulls 16 Tags Updated 7 months ago
-
qwen3-vl-abliterated
The most powerful vision-language model in the Qwen3 model family to date.
vision tools thinking 2b 4b 8b 30b 32b73.8K Pulls 54 Tags Updated 5 months ago
-
qwq-abliterated
QwQ is an experimental research model focused on advancing AI reasoning capabilities.
tools 32b70.5K Pulls 17 Tags Updated 1 year ago
-
glm-4.7-flash-abliterated
As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.
tools thinking52.2K Pulls 5 Tags Updated 2 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 32b44.1K Pulls 13 Tags Updated 1 year ago
-
llama3.2-abliterate
Meta's Llama 3.2 goes small with 1B and 3B models.
tools 1b 3b39.9K 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 14b39.8K Pulls 11 Tags Updated 1 year 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 72b39.6K Pulls 46 Tags Updated 11 months ago
-
gemma-4-abliterated
Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.
vision tools thinking audio e2b e4b 26b 31b 48b38.7K Pulls 29 Tags Updated 2 days ago
-
gpt-oss-abliterated
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
tools thinking 20b 120b38K Pulls 16 Tags Updated 6 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 8b35.5K Pulls 5 Tags Updated 1 year 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 70b32K Pulls 10 Tags Updated 1 year ago
-
gemma3n-abliterated
This is an uncensored version of google/gemma-3n created with abliteration
19.9K Pulls 2 Tags Updated 9 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 32b16.7K Pulls 31 Tags Updated 1 year 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 60b12.3K Pulls 40 Tags Updated 7 months ago
-
phi4-abliterated
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
14b12.2K Pulls 5 Tags Updated 1 year 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 1026b11K Pulls 4 Tags Updated 8 months ago
-
qwen3-coder-abliterated
Qwen3-Coder featuring the following key enhancements: Significant Performance, Long-context Capabilities, Agentic Coding.
30b 480b10.5K Pulls 9 Tags Updated 8 months ago
-
mistral-small-abliterated
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
tools 24b9,342 Pulls 10 Tags Updated 1 year ago
-
hy-mt1.5-abliterated
Hunyuan Translation Model Version 1.5 includes a 1.8B translation model, HY-MT1.5-1.8B, and a 7B translation mode
1.8b 7b8,306 Pulls 16 Tags Updated 3 months ago
-
baronllm-abliterated
This is an uncensored version of AlicanKiraz0/BaronLLM_Offensive_Security_LLM_Q6_K_GGUF created with abliteration
tools 8b7,305 Pulls 4 Tags Updated 10 months ago
-
deepseek-v3
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
7,167 Pulls 2 Tags Updated 1 year ago
-
hunyuan-mt-abliterated
The Hunyuan Translation Model comprises a translation model, Hunyuan-MT-7B, and an ensemble model, Hunyuan-MT-Chimera.
7b7,157 Pulls 9 Tags Updated 7 months ago
-
openthinker-abliterated
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
7b 32b6,455 Pulls 9 Tags Updated 1 year ago
-
magistral-abliterated
This is an uncensored version of mistralai/magistral-Small-2506 created with abliteration
thinking 24b6,284 Pulls 6 Tags Updated 10 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 32b6,213 Pulls 16 Tags Updated 5 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 2b6,019 Pulls 5 Tags Updated 1 year 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 3.8b5,604 Pulls 5 Tags Updated 1 year ago
-
qwen3-coder-next-abliterated
Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.
tools4,994 Pulls 4 Tags Updated 2 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 80b4,824 Pulls 10 Tags Updated 4 months ago
-
dolphin3-r1-abliterated
Dolphin's first generation reasoning models.
24b4,742 Pulls 10 Tags Updated 1 year ago
-
deepseek-v3-abliterated
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
671b3,643 Pulls 5 Tags Updated 1 year ago
-
devstral-abliterated
This is an uncensored version of mistralai/Devstral-Small-2505 created with abliteration
tools 24b3,640 Pulls 6 Tags Updated 10 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
8b3,491 Pulls 6 Tags Updated 1 year ago
-
homunculus-abliterated
This is an uncensored version of arcee-ai/Homunculus created with abliteration
thinking 12b2,998 Pulls 5 Tags Updated 10 months ago
-
seed-coder-abliterate
This is an uncensored version of ByteDance-Seed/Seed-Coder-8B-Instruct created with abliteration
2,906 Pulls 5 Tags Updated 11 months ago
-
jan-nano-abliterated
This is an uncensored version of Menlo/Jan-nano created with abliteration
tools thinking 4b2,871 Pulls 10 Tags Updated 9 months ago
-
am-thinking-abliterate
This is an uncensored version of a-m-team/AM-Thinking-v1 created with abliteration
tools 32b2,845 Pulls 6 Tags Updated 11 months ago
-
qwenlong-abliterated
This is an uncensored version of Tongyi-Zhiwen/QwenLong-L1-32B created with abliteration
thinking 32b2,840 Pulls 5 Tags Updated 10 months ago
-
phi4-reasoning-abliterated
Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.
3.8b2,813 Pulls 4 Tags Updated 11 months ago
-
lfm2.5-abliterated
LFM2.5 is a new family of hybrid models designed for on-device deployment.
tools 1.2b2,784 Pulls 10 Tags Updated 2 months 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 30b2,657 Pulls 5 Tags Updated 6 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.
8b2,600 Pulls 5 Tags Updated 11 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 8b2,517 Pulls 11 Tags Updated 1 year 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.
70b2,435 Pulls 9 Tags Updated 1 year 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.
32b2,362 Pulls 6 Tags Updated 1 year 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
32b2,359 Pulls 14 Tags Updated 1 year ago
-
aya-expanse-abliterated
Cohere For AI's language models trained to perform well across 23 different languages.
tools 8b 32b2,314 Pulls 9 Tags Updated 1 year 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.
24b2,244 Pulls 5 Tags Updated 1 year 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 3b2,231 Pulls 5 Tags Updated 1 year ago
-
acereason-nemotron-abliterated
This is an uncensored version of nvidia/AceReason-Nemotron created with abliteration Edit
7b 14b2,175 Pulls 9 Tags Updated 10 months 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 72b2,143 Pulls 18 Tags Updated 4 months ago
-
fara-abliterated
Fara-7B is Microsoft's first agentic small language model (SLM) designed specifically for computer use.
vision 7b2,097 Pulls 5 Tags Updated 4 months ago
-
qwenlong-l1.5-abliterated
QwenLong-L1.5, a long-context reasoning model built upon Qwen3-30B-A3B-Thinking, augmented with memory mechanisms to process tasks far beyond its physical context window.
tools thinking 30b2,006 Pulls 8 Tags Updated 3 months ago
-
exaone-deep-abliterated
This is an uncensored version of LGAI-EXAONE/EXAONE-Deep-2.4B created with abliteration
2.4b 7.8b1,888 Pulls 9 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 8b1,873 Pulls 5 Tags Updated 1 year 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.
1.5b1,870 Pulls 3 Tags Updated 1 year 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 10b1,622 Pulls 21 Tags Updated 1 year ago
-
llama3.3-abliterated-ft
The fine-tuned version of huihui_ai/llama3.3-abliterated
tools 70b1,601 Pulls 4 Tags Updated 1 year 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 32b1,565 Pulls 6 Tags Updated 1 year 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 8b1,545 Pulls 5 Tags Updated 4 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.
2.1b1,392 Pulls 5 Tags Updated 1 year ago
-
marco-o1-abliterated
An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).
7b1,391 Pulls 5 Tags Updated 1 year 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.
411b1,356 Pulls 5 Tags Updated 1 year 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 8b1,211 Pulls 11 Tags Updated 1 year 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 32b1,172 Pulls 14 Tags Updated 1 year ago
-
smallthinker-abliterated
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
3b1,152 Pulls 5 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.
8b1,060 Pulls 5 Tags Updated 1 year 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 7b983 Pulls 5 Tags Updated 1 year 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.
70b964 Pulls 10 Tags Updated 1 year ago
-
huihui-moe
Huihui-MoE is a Mixture of Experts (MoE) language model developed by huihui.ai
tools thinking 1.2b 23b952 Pulls 10 Tags Updated 9 months ago
-
nemotron-v1-abliterated
Llama Nemotron, Open, Production-ready Enterprise Models
tools 8b951 Pulls 6 Tags Updated 12 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 32b880 Pulls 7 Tags Updated 1 year ago
-
microthinker
MicroThinker is an experimental research model focused on advancing AI reasoning capabilities.
tools 1b 3b 8b823 Pulls 12 Tags Updated 1 year 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 70b802 Pulls 9 Tags Updated 1 year 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 480b739 Pulls 4 Tags Updated 8 months ago
-
glm-4.7-abliterated
Advancing the Coding Capability
tools thinking662 Pulls 1 Tag Updated 2 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 1026b611 Pulls 6 Tags Updated 4 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 70b555 Pulls 6 Tags Updated 1 year 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.
504 Pulls 2 Tags Updated 1 year ago
-
uwu-abliterated
UwU is an experimental research model focused on advancing AI reasoning capabilities.
7b461 Pulls 5 Tags Updated 1 year ago
-
glm4.6-abliterated
Advanced agentic, reasoning and coding capabilities.
tools thinking 357b426 Pulls 4 Tags Updated 4 months ago
-
s1.1-abliterated
This model is a successor of s1-32B with slightly better performance.
tools 32b373 Pulls 4 Tags Updated 1 year 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 32b348 Pulls 9 Tags Updated 1 year ago
-
devstral-2-abliterated
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
tools 123b345 Pulls 5 Tags Updated 3 months ago
-
Lucie-abliterated
Lucie-7B is a pretrained 7B parameter causal language model built by LINAGORA and OpenLLM-France.
7b338 Pulls 5 Tags Updated 1 year ago
-
fluentlylm-prinum-abliterated
fluently-lm/FluentlyLM-Prinum
tools 32b255 Pulls 5 Tags Updated 1 year 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 671b235 Pulls 12 Tags Updated 10 months ago
-
huihui3.5
Huihui 3.5 is a family of models created by remixing and merging multiple Qwen3.5 models of the same size.
vision tools thinking 67b222 Pulls 1 Tag Updated 1 week ago
-
skyt1-abliterated
Sky-T1-32B-Preview is an experimental research model focused on advancing AI reasoning capabilities
tools 32b213 Pulls 5 Tags Updated 1 year 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 3b193 Pulls 15 Tags Updated 11 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 671b183 Pulls 3 Tags Updated 7 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 7b166 Pulls 6 Tags Updated 1 year 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.
411b87 Pulls 3 Tags Updated 1 year ago