Qwen3-VL-2B-Instruct-FP8 is the FP8 quantized version of the most powerful vision-language model in the Qwen series. It uses fine-grained fp8 quantization with a block size of 128, and its performance is almost the same as that of the original BF16 model. This model has excellent text understanding and generation capabilities, in-depth visual perception and reasoning abilities, long context support, and enhanced spatial and video dynamic understanding abilities.

MultimodalTransformers

Qwen3-VL-32B-Instruct-FP8 is the FP8 quantized version of the most powerful vision-language model in the Qwen series. It uses fine-grained fp8 quantization with a block size of 128, and its performance metrics are almost the same as the original BF16 model. This model has excellent text understanding and generation capabilities, in-depth visual perception and reasoning abilities, long context support, and strong spatial and video dynamic understanding capabilities.

MultimodalTransformers

Qwen3-VL-32B-Thinking-FP8 is the FP8 quantized version of the most powerful vision-language model in the Qwen series. It uses fine-grained fp8 quantization technology with a block size of 128, and its performance indicators are almost the same as those of the original BF16 model. This model has excellent text understanding and generation capabilities, in-depth visual perception and reasoning abilities, long context support, and powerful agent interaction capabilities.

MultimodalSafetensors

Qwen3-VL-30B-A3B-Thinking-FP8 is the FP8 quantized version of the most powerful vision-language model in the Tongyi series. It uses fine-grained fp8 quantization with a block size of 128, and its performance indicators are almost the same as those of the original BF16 model. This model has excellent text understanding and generation capabilities, in-depth visual perception and reasoning abilities, and supports long contexts and video understanding.

MultimodalSafetensors

Qwen3-VL-30B-A3B-Instruct-FP8 is the FP8 quantized version of the most powerful vision-language model in the Tongyi series. It uses fine-grained FP8 quantization with a block size of 128, and its performance is almost the same as that of the original BF16 model. This model has excellent text understanding and generation capabilities, in-depth visual perception and reasoning capabilities, long context support, and strong agent interaction capabilities.

MultimodalSafetensors

Qwen3-VL-235B-A22B-Thinking-FP8 is the FP8 quantized version of the most powerful vision-language model in the Tongyi series. It uses fine-grained fp8 quantization with a block size of 128, and its performance metrics are almost the same as those of the original BF16 model. This model has excellent text understanding and generation capabilities, in-depth visual perception and reasoning capabilities, long context support, and strong agent interaction capabilities.

MultimodalSafetensors

Qwen3-VL-235B-A22B-Instruct-FP8 is the FP8 quantized version of the most powerful vision-language model in the Tongyi series. It uses fine-grained fp8 quantization with a block size of 128, and its performance is almost the same as that of the original BF16 model. This model has excellent text understanding and generation capabilities, in-depth visual perception and reasoning abilities, long context support, and strong spatial and video dynamic understanding abilities.

MultimodalSafetensors

GLM 4.6 is a quantized model optimized for a configuration of 128GB memory + single GPU. It uses the IQ_K quantization method, providing better quality and performance than the mainstream llama.cpp at the same size. This model needs to be used with ik_llama.cpp. On a configuration of 128GB dual-channel DDR5 memory, a single CCD Ryzen 7000 processor + a single 3090 graphics card, the text generation speed can reach approximately 6.8 tokens per second.

Natural Language ProcessingGgufMultiple Languages

VibeVoice-Large-Q8 is the first truly usable 8-bit VibeVoice model. Through selective quantization technology, it significantly reduces the model size while maintaining the same audio quality as the original model, making it suitable for scenarios with limited video memory.

Audio ProcessingTransformersMultiple Languages

MobileLLM-Pro is a 1-billion-parameter efficient device-side language model launched by Meta, optimized for mobile devices, supporting a context length of 128k and providing high-quality inference capabilities. This model is trained using knowledge distillation technology, outperforming models of the same scale in multiple benchmark tests, and supporting nearly lossless 4-bit quantization.

Natural Language ProcessingTransformersEnglish

KONI-4B-instruct-20250901 is a large language model developed by the Korea Institute of Science and Technology Information (KISTI) focusing on the technology field. It supports Korean and English and performs excellently in various scientific benchmark tests, outperforming other pre-trained models of the same scale.

Natural Language ProcessingTransformersMultiple Languages

Gemma 3 270M is a lightweight multimodal model launched by Google. Based on the same research technology as the Gemini series, it supports text and image input, has a 32K context window, and provides high-quality output in tasks such as question answering, summarization, image understanding, and code generation.

MultimodalTransformersMultiple Languages

Jet - Nemotron - 4B is an efficient hybrid architecture language model launched by NVIDIA. It is built based on two core innovations: post - neural architecture search and the JetBlock linear attention module. In terms of performance, it surpasses open - source models such as Qwen3, Qwen2.5, Gemma3, and Llama3.2. At the same time, it achieves a maximum of 53.6 times acceleration in generation throughput on the H100 GPU.

Natural Language ProcessingTransformersEnglish

Gemma 3 is a lightweight, state-of-the-art open-source model family launched by Google, built on the same research and technology as the Gemini model. This model has multimodal processing capabilities, supports text and image inputs, and generates text outputs, making it suitable for various text generation and image understanding tasks.

MultimodalTransformers

Gemma 3 is a lightweight and state-of-the-art open model family launched by Google, built on the same research and technology as the Gemini model. It has multi-modal processing capabilities, supports text and image inputs, and generates text outputs, suitable for various text generation and image understanding tasks.

MultimodalTransformers

GLM-4.5V-AWQ-4bit is a quantized multimodal model built on Zhipu AI's next-generation flagship text foundation model. Optimized by AWQ-4bit quantization technology, it significantly reduces the computational resource requirements while maintaining excellent performance. This model achieves SOTA performance among models of the same scale in 42 public visual language benchmark tests and has powerful visual reasoning capabilities.

MultimodalTransformersMultiple Languages

Gemma 3 is a lightweight open-source multimodal model series launched by Google, built on the same technology as Gemini. The 270M version is the smallest model in the series, supporting text and image input, with a 128K context window, suitable for deployment in resource-constrained environments.

MultimodalTransformers

Gemma 3 is a lightweight open-source multimodal model family launched by Google, built on the same research technology as Gemini. The 270M version is the smallest instruction-tuned model among them, supporting over 140 languages and having a 32K context length, suitable for text generation tasks in resource-constrained environments.

MultimodalTransformers

Gemma 3 is a lightweight and state-of-the-art open-source multimodal model family launched by Google, built on the same research and technology as the Gemini model. The 270M version is the smallest model among them, capable of handling text and image inputs and generating text outputs, suitable for various text generation and image understanding tasks.

MultimodalTransformers

Gemma 3 is a lightweight and state-of-the-art multimodal open model family launched by Google, built on the same research and technology as the Gemini model. This model can handle text and image inputs and generate text outputs. It has a large context window of 128K and supports over 140 languages, offering various sizes ranging from 270M to 27B.

MultimodalTransformers