This is a highly optimized, quantized version of the Qwen 3.6 35B model using NVFP4 precision for accelerated inference. It supports both text and vision inputs while maintaining strong performance. Distributed via Hugging Face, it is designed for developers needing fast multimodal inference on consumer or enterprise GPUs with Unsloth and Transformers compatibility.
Qwen3.6 35B A3B NVFP4 Fast is a Foundation models & chat product. It focuses on running large multimodal language models efficiently on limited hardware with minimal latency. It is built as an open-source project for developers. Qwen3.6 35B A3B NVFP4 Fast is open source under the Apache-2.0 license. Qwen3.6 35B A3B NVFP4 Fast is available on the web, the command line, and API.
Behind Qwen3.6 35B A3B NVFP4 Fast is Unsloth, and the product first shipped in 2023. Development happens publicly on GitHub with 68.7k stars and 1.2k commits in the last 90 days. The category is crowded — PulseGate's index counts 25 comparable apps. Key capabilities include Multimodal Inference, Fast Quantized Inference, and Vision-Language Processing. It exposes integrations via a public API.
Latest indexed changes and source events
unsloth/Qwen3.6-35B-A3B-NVFP4-Fast verified by the PulseGate indexer
Other apps tracked under the same category.
