Model Gallery
Discover and install AI models from our curated collection
Find Your Perfect Model
Filter by Model Type
Browse by Tags
gemma-4-26b-a4b-it-apex
AI model: gemma-4-26b-a4b-it-apex
Repository: localai
gemma-4-26b-a4b-it
Google Gemma 4 26B-A4B-IT is an open-source multimodal Mixture-of-Experts model with 26B total parameters and 4B active parameters. It handles text and image input, generating text output, with a 256K context window and support for 140+ languages. The MoE architecture provides strong performance with efficient inference. Well-suited for question answering, summarization, reasoning, and image understanding tasks.
Repository: localaiLicense: gemma
gemma-4-e4b-it
Google Gemma 4 E4B-IT is an open-source multimodal model with 8B total parameters and 4B effective parameters using selective parameter activation. It handles text and image input, generating text output, with a 256K context window and support for 140+ languages. Offers a good balance of performance and efficiency for deployment on consumer hardware.
Repository: localaiLicense: gemma
qwen_qwen3.5-4b
Repository: localai
qwen3.5-4b-claude-4.6-opus-reasoning-distilled
Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF - A GGUF quantized model optimized for local inference. Specialized for reasoning and chain-of-thought tasks. Based on Qwen 3.5 architecture with enhanced language understanding. Available in multiple quantization levels for various hardware requirements. Distilled from Claude-style reasoning models for enhanced logical reasoning capabilities.
Repository: localai
voxtral-mini-4b-realtime
Voxtral Mini 4B Realtime is a speech-to-text model from Mistral AI. It is a 4B parameter model optimized for fast, accurate audio transcription with low latency, making it ideal for real-time applications. The model uses the Voxtral architecture for efficient audio processing.
Repository: localaiLicense: apache-2.0
acestep-cpp-turbo-4b
ACE-Step 1.5 Turbo (C++ / GGML) with 4B LM — higher quality music generation from text and lyrics.
Uses the larger 4B parameter LM for better metadata/code generation. Stereo 48kHz output.
Repository: localaiLicense: mit
qwen3-vl-4b-instruct
Qwen3-VL-4B-Instruct is the 4B parameter model of the Qwen3-VL series.
Repository: localaiLicense: apache-2.0
qwen3-vl-4b-thinking
Qwen3-VL-4B-Thinking is the 4B parameter model of the Qwen3-VL series that is thinking.
Repository: localaiLicense: apache-2.0
opengvlab_internvl3_5-14b-q8_0
We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.
Repository: localaiLicense: apache-2.0
opengvlab_internvl3_5-14b
We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.
Repository: localaiLicense: apache-2.0
opengvlab_internvl3_5-4b
We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.
Repository: localaiLicense: apache-2.0
opengvlab_internvl3_5-4b-q8_0
We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.
Repository: localaiLicense: apache-2.0
qwen3-14b
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.
Qwen3-14B has the following features:
Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 14.8B
Number of Paramaters (Non-Embedding): 13.2B
Number of Layers: 40
Number of Attention Heads (GQA): 40 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
qwen3-4b
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.
Qwen3-4B has the following features:
Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 4.0B
Number of Paramaters (Non-Embedding): 3.6B
Number of Layers: 36
Number of Attention Heads (GQA): 32 for Q and 8 for KV
Context Length: 32,768 natively and 131,072 tokens with YaRN.
Repository: localaiLicense: apache-2.0
mlabonne_qwen3-14b-abliterated
Qwen3-14B-abliterated is a 14B parameter model that is abliterated.
Repository: localaiLicense: apache-2.0
mlabonne_qwen3-4b-abliterated
Qwen3-4B-abliterated is a 4B parameter model that is abliterated.
Repository: localaiLicense: apache-2.0
qwen3-8b-jailbroken
This jailbroken LLM is released strictly for academic research purposes in AI safety and model alignment studies. The author bears no responsibility for any misuse or harm resulting from the deployment of this model. Users must comply with all applicable laws and ethical guidelines when conducting research.
A jailbroken Qwen3-8B model using weight orthogonalization[1].
Implementation script: https://gist.github.com/cooperleong00/14d9304ba0a4b8dba91b60a873752d25
[1]: Arditi, Andy, et al. "Refusal in language models is mediated by a single direction." arXiv preprint arXiv:2406.11717 (2024).
Repository: localaiLicense: apache-2.0
fast-math-qwen3-14b
By applying SFT and GRPO on difficult math problems, we enhanced the performance of DeepSeek-R1-Distill-Qwen-14B and developed Fast-Math-R1-14B, which achieves approx. 30% faster inference on average, while maintaining accuracy.
In addition, we trained and open-sourced Fast-Math-Qwen3-14B, an efficiency-optimized version of Qwen3-14B`, following the same approach.
Compared to Qwen3-14B, this model enables approx. 65% faster inference on average, with minimal loss in performance.
Technical details can be found in our github repository.
Note: This model likely inherits the ability to perform inference in TIR mode from the original model. However, all of our experiments were conducted in CoT mode, and its performance in TIR mode has not been evaluated.
Repository: localaiLicense: apache-2.0
amoral-qwen3-14b
Core Function:
Produces analytically neutral responses to sensitive queries
Maintains factual integrity on controversial subjects
Avoids value-judgment phrasing patterns
No inherent moral framing ("evil slop" reduction)
Emotionally neutral tone enforcement
Epistemic humility protocols (avoids "thrilling", "wonderful", etc.)
Repository: localaiLicense: apache-2.0
huihui-ai_qwen3-14b-abliterated
This is an uncensored version of Qwen/Qwen3-14B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
Ablation was performed using a new and faster method, which yields better results.
Repository: localaiLicense: apache-2.0
Page
1
of many