Filter by type:
Filter by tags:
qwen3.6-40b-claude-4.6-opus-deckard-heretic-uncensored-thinking-neo-code-di-imatrix-max
The Qwen 3.5 version (also 40B) got 181 likes+ This version uses the new Qwen 3.6 27B arch (which exceeds even Qwen's own 398B model).
WARNING: This model has character and intelligence. It will take no prisoners. It will give no quarter. Uncensored,
Unfiltered and boldly confident. Not even remotely "SFW", if you ask it for NSFW content. And it is wickedly smart too - exceeding the base model in 6 out of 7 benchmarks.
Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking
40 billion parameters (dense, not moe) expanded from 27B Qwen 3.6, then trained on Claude 4.6 Opus High Reasoning dataset via Unsloth on local hardware... but there
is much more to the story - in comes DECKARD.
96 layers, 1275 Tensors. (50% more than base model of 27B)
Features variable length reasoning ; less complex = shorter, longer for more complex.
Model performance has increased dramatically. And it has character too.
A lot of character.
No censorship, no nanny. (via Heretic)
And it is very, very smart.
...
Repository: localaiLicense: apache-2.0
nemotron-3-nano-omni-30b-a3b-reasoning-apex
# Model Overview
### Description:
NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows. It extends the Nemotron Nano family with integrated video+speech comprehension, Graphical User Interface (GUI), Optical Character Recognition (OCR), and speech transcription capabilities, enabling end-to-end processing of rich enterprise content such as meeting recordings, M&E assets, training videos, and complex business documents. NVIDIA Nemotron 3 Nano Omni was developed by NVIDIA as part of the Nemotron model family.
This model is available for commercial use.
This model was improved using Qwen3-VL-30B-A3B-Instruct, Qwen3.5-122B-A10B, Qwen3.5-397B-A17B, Qwen2.5-VL-72B-Instruct, and gpt-oss-120b. For more information, please see the Training Dataset section below.
### License/Terms of Use
Governing Terms: Use of this model is governed by the NVIDIA Open Model Agreement
### Deployment Geography:
Global
...
Repository: localaiLicense: other
qwen3.5-397b-a17b
Repository: localaiLicense: apache-2.0
qwen3.5-27b
Repository: localaiLicense: apache-2.0
qwen3.5-122b-a10b
Repository: localaiLicense: apache-2.0
qwen3-coder-next-mxfp4_moe
The model is a quantized version of **Qwen/Qwen3-Coder-Next** (base model) using the **MXFP4** quantization scheme. It is optimized for efficiency while retaining performance, suitable for deployment in applications requiring lightweight inference. The quantized version is tailored for specific tasks, with parameters like temperature=1.0 and top_p=0.95 recommended for generation.
Repository: localai
glm-4.7-flash
**GLM-4.7-Flash** is a 30B-A3B MoE (Model Organism Ensemble) model designed for efficient deployment. It outperforms competitors in benchmarks like AIME 25, GPQA, and τ²-Bench, offering strong accuracy while balancing performance and efficiency. Optimized for lightweight use cases, it supports inference via frameworks like vLLM and SGLang, with detailed deployment instructions in the official repository. Ideal for applications requiring high-quality text generation with minimal resource consumption.
Repository: localaiLicense: mit
ibm-granite_granite-4.0-h-small
Granite-4.0-H-Small is a 32B parameter long-context instruct model finetuned from Granite-4.0-H-Small-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets. This model is developed using a diverse set of techniques with a structured chat format, including supervised finetuning, model alignment using reinforcement learning, and model merging. Granite 4.0 instruct models feature improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
Repository: localaiLicense: apache-2.0
ibm-granite_granite-4.0-h-micro
Granite-4.0-H-Micro is a 3B parameter long-context instruct model finetuned from Granite-4.0-H-Micro-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets. This model is developed using a diverse set of techniques with a structured chat format, including supervised finetuning, model alignment using reinforcement learning, and model merging. Granite 4.0 instruct models feature improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
Repository: localaiLicense: apache-2.0
baidu_ernie-4.5-21b-a3b-thinking
Over the past three months, we have continued to scale the thinking capability of ERNIE-4.5-21B-A3B, improving both the quality and depth of reasoning, thereby advancing the competitiveness of ERNIE lightweight models in complex reasoning tasks. We are pleased to introduce ERNIE-4.5-21B-A3B-Thinking, featuring the following key enhancements:
Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, text generation, and academic benchmarks that typically require human expertise.
Efficient tool usage capabilities.
Enhanced 128K long-context understanding capabilities.
Note: This version has an increased thinking length. We strongly recommend its use in highly complex reasoning tasks. ERNIE-4.5-21B-A3B-Thinking is a text MoE post-trained model, with 21B total parameters and 3B activated parameters for each token.
Repository: localaiLicense: apache-2.0
liquidai_lfm2-8b-a1b
LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.
We're releasing the weights of our first MoE based on LFM2, with 8.3B total parameters and 1.5B active parameters.
LFM2-8B-A1B is the best on-device MoE in terms of both quality (comparable to 3-4B dense models) and speed (faster than Qwen3-1.7B).
Code and knowledge capabilities are significantly improved compared to LFM2-2.6B.
Quantized variants fit comfortably on high-end phones, tablets, and laptops.
Repository: localaiLicense: lfm1.0
gpt-oss-20b
Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
We’re releasing two flavors of the open models:
gpt-oss-120b — for production, general purpose, high reasoning use cases that fits into a single H100 GPU (117B parameters with 5.1B active parameters)
gpt-oss-20b — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)
Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.
This model card is dedicated to the smaller gpt-oss-20b model. Check out gpt-oss-120b for the larger model.
Highlights
Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
Full chain-of-thought: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.
Fine-tunable: Fully customize models to your specific use case through parameter fine-tuning.
Agentic capabilities: Use the models’ native capabilities for function calling, web browsing, Python code execution, and Structured Outputs.
Native MXFP4 quantization: The models are trained with native MXFP4 precision for the MoE layer, making gpt-oss-120b run on a single H100 GPU and the gpt-oss-20b model run within 16GB of memory.
Repository: localaiLicense: apache-2.0
gpt-oss-120b
Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
We’re releasing two flavors of the open models:
gpt-oss-120b — for production, general purpose, high reasoning use cases that fits into a single H100 GPU (117B parameters with 5.1B active parameters)
gpt-oss-20b — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)
Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.
This model card is dedicated to the smaller gpt-oss-20b model. Check out gpt-oss-120b for the larger model.
Highlights
Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
Full chain-of-thought: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.
Fine-tunable: Fully customize models to your specific use case through parameter fine-tuning.
Agentic capabilities: Use the models’ native capabilities for function calling, web browsing, Python code execution, and Structured Outputs.
Native MXFP4 quantization: The models are trained with native MXFP4 precision for the MoE layer, making gpt-oss-120b run on a single H100 GPU and the gpt-oss-20b model run within 16GB of memory.
Repository: localaiLicense: apache-2.0
openai_gpt-oss-20b-neo
These are NEO Imatrix GGUFs, NEO dataset by DavidAU.
NEO dataset improves overall performance, and is for all use cases.
Example output below (creative), using settings below.
Model also passed "hard" coding test too (6 experts); no issues (IQ4_NL).
(Forcing the model to create code with no dependencies and limits of coding short cuts, with multiple loops, and in real time with no blocking in a language that does not support it normally.)
Due to quanting issues with this model (which result in oddball quant sizes / mixtures), only TESTED quants will be uploaded (at the moment).
Repository: localaiLicense: apache-2.0
openai-gpt-oss-20b-abliterated-uncensored-neo-imatrix
These are NEO Imatrix GGUFs, NEO dataset by DavidAU.
NEO dataset improves overall performance, and is for all use cases.
This model uses Huihui-gpt-oss-20b-BF16-abliterated as a base which DE-CENSORS the model and removes refusals.
Example output below (creative; IQ4_NL), using settings below.
This model can be a little rough around the edges (due to abliteration) ; make sure you see the settings below for best operation.
It can also be creative, off the shelf crazy and rational too.
Enjoy!
Repository: localaiLicense: apache-2.0
qwen3-30b-a3b
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.
Qwen3-30B-A3B has the following features:
Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 30.5B in total and 3.3B activated
Number of Paramaters (Non-Embedding): 29.9B
Number of Layers: 48
Number of Attention Heads (GQA): 32 for Q and 4 for KV
Number of Experts: 128
Number of Activated Experts: 8
Context Length: 32,768 natively and 131,072 tokens with YaRN.
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.
Repository: localaiLicense: apache-2.0
qwen3-235b-a22b-instruct-2507
We introduce the updated version of the Qwen3-235B-A22B non-thinking mode, named Qwen3-235B-A22B-Instruct-2507, featuring the following key enhancements:
Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.
Substantial gains in long-tail knowledge coverage across multiple languages.
Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation.
Enhanced capabilities in 256K long-context understanding.
Repository: localaiLicense: apache-2.0
qwen3-coder-480b-a35b-instruct
Today, we're announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we're excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct. featuring the following key enhancements:
Significant Performance among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks, achieving results comparable to Claude Sonnet.
Long-context Capabilities with native support for 256K tokens, extendable up to 1M tokens using Yarn, optimized for repository-scale understanding.
Agentic Coding supporting for most platform such as Qwen Code, CLINE, featuring a specially designed function call format.
Repository: localaiLicense: apache-2.0
qwen3-32b
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.
Qwen3-32B has the following features:
Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 32.8B
Number of Paramaters (Non-Embedding): 31.2B
Number of Layers: 64
Number of Attention Heads (GQA): 64 for Q and 8 for KV
Context Length: 32,768 natively and 131,072 tokens with YaRN.
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.
Repository: localaiLicense: apache-2.0
qwen3-30b-a1.5b-high-speed
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly.
This is a simple "finetune" of the Qwen's "Qwen 30B-A3B" (MOE) model, setting the experts in use from 8 to 4 (out of 128 experts).
This method close to doubles the speed of the model and uses 1.5B (of 30B) parameters instead of 3B (of 30B) parameters. Depending on the application you may want to use the regular model ("30B-A3B"), and use this model for simpler use case(s) although I did not notice any loss of function during routine (but not extensive) testing.
Example generation (Q4KS, CPU) at the bottom of this page using 4 experts / this model.
More complex use cases may benefit from using the normal version.
For reference:
Cpu only operation Q4KS (windows 11) jumps from 12 t/s to 23 t/s.
GPU performance IQ3S jumps from 75 t/s to over 125 t/s. (low to mid level card)
Context size: 32K + 8K for output (40k total)
Repository: localaiLicense: apache-2.0
kalomaze_qwen3-16b-a3b
A man-made horror beyond your comprehension.
But no, seriously, this is my experiment to:
measure the probability that any given expert will activate (over my personal set of fairly diverse calibration data), per layer
prune 64/128 of the least used experts per layer (with reordered router and indexing per layer)
It can still write semi-coherently without any additional training or distillation done on top of it from the original 30b MoE. The .txt files with the original measurements are provided in the repo along with the exported weights.
Custom testing to measure the experts was done on a hacked version of vllm, and then I made a bespoke script to selectively export the weights according to the measurements.
Repository: localaiLicense: apache-2.0
Page 1