Filter by type:
Filter by tags:
qwen_qwen3.5-35b-a3b
Qwen3.5-35B-A3B is a quantized multimodal language model with 35B parameters using an A3B MoE architecture. It supports image-text understanding and chat interactions via llama-cpp backend.
Repository: localaiLicense: apache-2.0
qwen_qwen3.5-0.8b
Qwen 3.5 0.8B parameter model quantized for llama-cpp backend. Supports chat interactions and multimodal image-text inputs.
Repository: localaiLicense: apache-2.0
qwen_qwen3.5-2b
Qwen3.5-2B is a highly efficient, instruction-tuned multilingual language model available in various quantized GGUF formats. Optimized for llama-cpp inference, it supports chat and completion tasks with strong performance on low-RAM hardware. The model is available in multiple quantization levels ranging from Q8_0 to IQ2_M to balance quality and resource usage.
Repository: localaiLicense: apache-2.0
qwen_qwen3.5-4b
Qwen3.5-4B is a multimodal LLM with 4 billion parameters, optimized for chat and vision tasks. This GGUF quantized version enables efficient local inference via llama-cpp backend. Supports both text and image input for enhanced conversational capabilities.
Repository: localaiLicense: apache-2.0
qwen_qwen3-next-80b-a3b-thinking
Repository: localaiLicense: apache-2.0
nanbeige4.1-3b-q4
Nanbeige4.1-3B is built upon Nanbeige4-3B-Base and represents an enhanced iteration of our previous reasoning model, Nanbeige4-3B-Thinking-2511, achieved through further post-training optimization with supervised fine-tuning (SFT) and reinforcement learning (RL). As a highly competitive open-source model at a small parameter scale, Nanbeige4.1-3B illustrates that compact models can simultaneously achieve robust reasoning, preference alignment, and effective agentic behaviors.
Key features:
Strong Reasoning: Capable of solving complex, multi-step problems through sustained and coherent reasoning within a single forward pass, reliably producing correct answers on benchmarks like LiveCodeBench-Pro, IMO-Answer-Bench, and AIME 2026 I.
Robust Preference Alignment: Outperforms same-scale models (e.g., Qwen3-4B-2507, Nanbeige4-3B-2511) and larger models (e.g., Qwen3-30B-A3B, Qwen3-32B) on Arena-Hard-v2 and Multi-Challenge.
Agentic Capability: First general small model to natively support deep-search tasks and sustain complex problem-solving with >500 rounds of tool invocations; excels in benchmarks like xBench-DeepSearch (75), Browse-Comp (39), and others.
Repository: localaiLicense: apache-2.0
mox-small-1-i1
The model, **vanta-research/mox-small-1**, is a small-scale text-generation model optimized for conversational AI tasks. It supports chat, persona research, and chatbot applications. The quantized versions (e.g., i1-Q4_K_M, i1-Q4_K_S) are available for efficient deployment, with the i1-Q4_K_S variant offering the best balance of size, speed, and quality. The model is designed for lightweight inference and is compatible with frameworks like HuggingFace Transformers.
Repository: localaiLicense: apache-2.0
tildeopen-30b-instruct-lv-i1
The **TildeOpen-30B-Instruct-LV-i1-GGUF** is a quantized version of the base model **pazars/TildeOpen-30B-Instruct-LV**, optimized for deployment. It is an instruct-based language model trained on diverse datasets, supporting multiple languages (en, de, fr, pl, ru, it, pt, cs, nl, es, fi, tr, hu, bg, uk, bs, hr, da, et, lt, ro, sk, sl, sv, no, lv, sr, sq, mk, is, mt, ga). Licensed under CC-BY-4.0, it uses the Transformers library and is designed for efficient inference. The quantized version (with imatrix format) is tailored for deployment on devices with limited resources, while the base model remains the original, high-quality version.
Repository: localaiLicense: cc-by-4.0
qwen3-omni-30b-a3b-instruct
Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation model. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. This GGUF build runs on llama.cpp with the bundled mmproj for multimodal inputs.
Repository: localaiLicense: apache-2.0
qwen3-omni-30b-a3b-thinking
Qwen3-Omni-30B-A3B-Thinking is the reasoning-enhanced variant of Qwen3-Omni, a natively end-to-end multilingual omni-modal foundation model. It processes text, images, and audio and produces chain-of-thought reasoning before the final answer. This GGUF build runs on llama.cpp with the bundled mmproj.
Repository: localaiLicense: apache-2.0
glm-ocr
GLM-OCR is a vision-language model specialized for optical character recognition and document understanding, built on the GLM architecture. This GGUF build runs on llama.cpp with the bundled mmproj.
Repository: localaiLicense: mit
deepseek-ocr
DeepSeek-OCR is a vision-language model from DeepSeek AI specialized for optical character recognition and document understanding. This GGUF build runs on llama.cpp with the bundled mmproj.
Repository: localaiLicense: mit
lfm2-vl-450m
LFM2‑VL is Liquid AI's first series of multimodal models, designed to process text and images with variable resolutions. Built on the LFM2 backbone, it is optimized for low-latency and edge AI applications.
We're releasing the weights of two post-trained checkpoints with 450M (for highly constrained devices) and 1.6B (more capable yet still lightweight) parameters.
2× faster inference speed on GPUs compared to existing VLMs while maintaining competitive accuracy
Flexible architecture with user-tunable speed-quality tradeoffs at inference time
Native resolution processing up to 512×512 with intelligent patch-based handling for larger images, avoiding upscaling and distortion
Repository: localaiLicense: lfm1.0
openbuddy_openbuddy-r1-0528-distill-qwen3-32b-preview0-qat
OpenBuddy distillation of Qwen3-32B from DeepSeek-R1, featuring 40K context window and multilingual support (zh, en, fr, de, ja, ko, it, fi). GGUF quantized version optimized for local inference with llama.cpp.
Repository: localaiLicense: apache-2.0
sicariussicariistuff_x-ray_alpha
This is a pre-alpha proof-of-concept of a real fully uncensored vision model.
Why do I say "real"? The few vision models we got (qwen, llama 3.2) were "censored," and their fine-tunes were made only to the text portion of the model, as training a vision model is a serious pain.
The only actually trained and uncensored vision model I am aware of is ToriiGate; the rest of the vision models are just the stock vision + a fine-tuned LLM.
Repository: localaiLicense: gemma
google-gemma-3-27b-it-qat-q4_0-small
This is a requantized version of https://huggingface.co/google/gemma-3-27b-it-qat-q4_0-gguf. The official QAT weights released by google use fp16 (instead of Q6_K) for the embeddings table, which makes this model take a significant extra amount of memory (and storage) compared to what Q4_0 quants are supposed to take. Requantizing with llama.cpp achieves a very similar result. Note that this model ends up smaller than the Q4_0 from Bartowski. This is because llama.cpp sets some tensors to Q4_1 when quantizing models to Q4_0 with imatrix, but this is a static quant. The perplexity score for this one is even lower with this model compared to the original model by Google, but the results are within margin of error, so it's probably just luck. I also fixed the control token metadata, which was slightly degrading the performance of the model in instruct mode.
Repository: localaiLicense: gemma
meta-llama_llama-4-scout-17b-16e-instruct
The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.
These Llama 4 models mark the beginning of a new era for the Llama ecosystem. We are launching two efficient models in the Llama 4 series, Llama 4 Scout, a 17 billion parameter model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts.
Repository: localaiLicense: llama4
eurollm-9b-instruct
The EuroLLM project has the goal of creating a suite of LLMs capable of understanding and generating text in all European Union languages as well as some additional relevant languages. EuroLLM-9B is a 9B parameter model trained on 4 trillion tokens divided across the considered languages and several data sources: Web data, parallel data (en-xx and xx-en), and high-quality datasets. EuroLLM-9B-Instruct was further instruction tuned on EuroBlocks, an instruction tuning dataset with focus on general instruction-following and machine translation.
Repository: localaiLicense: apache-2.0
virtuoso-lite
Virtuoso-Lite (10B) is our next-generation, 10-billion-parameter language model based on the Llama-3 architecture. It is distilled from Deepseek-v3 using ~1.1B tokens/logits, allowing it to achieve robust performance at a significantly reduced parameter count compared to larger models. Despite its compact size, Virtuoso-Lite excels in a variety of tasks, demonstrating advanced reasoning, code generation, and mathematical problem-solving capabilities.
Repository: localaiLicense: falcon-llm
suayptalha_maestro-10b
Maestro-10B is a 10 billion parameter model fine-tuned from Virtuoso-Lite, a next-generation language model developed by arcee-ai. Virtuoso-Lite itself is based on the Llama-3 architecture, distilled from Deepseek-v3 using approximately 1.1 billion tokens/logits. This distillation process allows Virtuoso-Lite to achieve robust performance with a smaller parameter count, excelling in reasoning, code generation, and mathematical problem-solving. Maestro-10B inherits these strengths from its base model, Virtuoso-Lite, and further enhances them through fine-tuning on the OpenOrca dataset. This combination of a distilled base model and targeted fine-tuning makes Maestro-10B a powerful and efficient language model.
Repository: localaiLicense: falcon-llm-license
intellect-1-instruct
INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.
This is an instruct model. The base model associated with it is INTELLECT-1.
INTELLECT-1 was trained on up to 14 concurrent nodes distributed across 3 continents, with contributions from 30 independent community contributors providing compute. The training code utilizes the prime framework, a scalable distributed training framework designed for fault-tolerant, dynamically scaling, high-perfomance training on unreliable, globally distributed workers. The key abstraction that allows dynamic scaling is the ElasticDeviceMesh which manages dynamic global process groups for fault-tolerant communication across the internet and local process groups for communication within a node. The model was trained using the DiLoCo algorithms with 100 inner steps. The global all-reduce was done with custom int8 all-reduce kernels to reduce the communication payload required, greatly reducing the communication overhead by a factor 400x.
Repository: localaiLicense: apache-2.0
Page 1