# Low-resource deployment

A quantized version of NVIDIA OpenReasoning - Nemotron - 32B, quantized through llama.cpp to reduce model storage and computational resource requirements for easy deployment.

The quantized version of NVIDIA OpenReasoning - Nemotron - 1.5B, optimized by the llama.cpp tool to improve the running efficiency and performance on different hardware.

This model is a GGUF format model converted from nvidia/OpenReasoning-Nemotron-32B and can be used with llama.cpp.

A quantized version of TheDrummer's Cydonia-24B-v4 model based on llama.cpp, which can run efficiently on devices with limited resources.

Voxtral Mini is an enhanced version based on Ministral 3B, with advanced audio input capabilities and excellent performance in speech transcription, translation, and audio understanding.

A GGUF format model file based on kyutai/helium-1-2b, quantized by TensorBlock, supporting multiple languages.

LFM2-1.2B is a multilingual text generation model with a parameter scale of 1.2B launched by LiquidAI, optimized for Apple Silicon chips.

This is a quantized version of the prithivMLmods/WR30a-Deep-7B-0711 model, supporting multiple languages and suitable for various tasks such as text generation and image caption generation.

A statically quantized version of the Gemma-3n-E2B-it model, supporting various speech and text processing tasks

DiffuCoder-7B-cpGRPO-8bit is a code generation model converted to MLX format, based on apple/DiffuCoder-7B-cpGRPO, and is specifically designed to provide developers with an efficient code generation tool.

A static quantization version of UniReason-Qwen3-14B-RL, suitable for text generation and mathematical reasoning research scenarios.

A static quantized version of the Google Gemma-3n-E2B model, offering various quantization types to balance model size and performance.

Gemma-3n-E4B-it is a model developed by Google, optimized through MLX quantization, and is particularly suitable for Apple Silicon devices.

This is a quantized version of the Austral-70B-Winton model by Delta-Vector. Through quantization technology, it reduces the storage and computational resource requirements of the model while maintaining good performance, making it suitable for scenarios with limited resources.

A quantized version of Gama-12B, providing files of various quantization types, suitable for text generation tasks and supporting English and Portuguese.

Gama-12B is a large language model supporting multiple languages, offering various quantized versions to meet different performance and precision requirements.

The LongWriter-Zero-32B quantized model is based on the THU-KEG/LongWriter-Zero-32B base model, supports both Chinese and English, and is suitable for long context scenarios such as reinforcement learning and writing.

Skywork-SWE-32B is a large language model with 32B parameters. It is quantized by Llamacpp imatrix and can run efficiently in resource-constrained environments.

This is a quantized version of the NVIDIA AceReason - Nemotron - 1.1 - 7B model, which optimizes the model's running efficiency on different hardware while maintaining certain performance and quality.

This is the quantized version of OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT. With quantization technology, the model can run more efficiently under different hardware conditions.

This is a quantized model based on ONNX, which is the uint8 quantized version of Qwen/Qwen3-Embedding-0.6B. It reduces the model size while maintaining retrieval performance.

This is a text-to-video quantization model that undergoes quantization conversion based on a specific base model and supports various video generation tasks.

This is a quantized text-to-video model that converts the base model to the GGUF format and can be used in ComfyUI, providing more options for text-to-video generation.

A 6-bit quantized version converted from the DeepSeek-R1-0528-Qwen3-8B model, suitable for text generation tasks in the MLX framework.

Blitzar-Coder-4B-F.1 is an efficient multilingual coding model fine-tuned based on Qwen3-4B, supporting more than 10 programming languages and having excellent code generation, debugging, and reasoning capabilities.

Home Llama 3.2 3B is fine-tuned based on Meta's Llama 3.2 3B model and is specifically designed for controlling home devices and performing basic Q&A tasks.

This project provides the GGUF quantized file for the Echelon-AI/Med-Qwen2-7B model, supported by Featherless AI, aiming to enhance model performance and reduce operating costs.

Gemma 3n is a lightweight and state-of-the-art open-source multimodal model family launched by Google. It is built on the same research and technology as the Gemini model and supports text, audio, and visual inputs.

Bielik-11B-v2.6-Instruct is a large Polish language model developed by SpeakLeash and ACK Cyfronet AGH, fine-tuned based on Bielik-11B-v2, suitable for instruction following tasks.

Phi-3.5-mini-instruct is a lightweight and advanced open-source model built on the dataset used by Phi-3, focusing on high-quality, inference-rich data. It supports a 128K token context length and has powerful multilingual and long-context processing capabilities.

A quantized model based on DeepSeek-R1-0528, focusing on text generation tasks and providing a more efficient way of use.

A quantized version based on the infly/inf-o1-pi0 model, supporting multilingual text generation tasks, optimized with llama.cpp's imatrix quantization.

medgemma-4b-it is a multimodal model focused on the medical field, capable of processing image and text inputs, and suitable for multiple medical scenarios such as radiology and clinical reasoning.

This is a 4-bit quantized language model in MLX format, suitable for text generation tasks.

KernelLLM is a large language model developed by Facebook. This version is quantized using the llama.cpp tool with imatrix, offering multiple quantization options to suit different hardware requirements.

This is the statically quantized version of the Nellyw888/VeriReason-Qwen2.5-1.5B-grpo-small model, focusing on Verilog code generation and reasoning tasks.

Llamacpp imatrix quantized version based on a-m-team/AM-Thinking-v1 model, supporting multiple quantization types, suitable for text generation tasks.

Qwen3 is the latest generation of large language models in the Qwen series, offering a dense model with 0.6B parameters, achieving breakthrough progress in reasoning, instruction following, agent capabilities, and multilingual support.

This is a 12B-parameter large language model, processed with llama.cpp's imatrix quantization, offering multiple quantized versions to accommodate different hardware requirements.

A 4-bit DWQ quantized MLX format version converted from the Google Gemma-3-4b-it model, providing efficient text generation capabilities