Qwen3-8B-FP8
An FP8 edition of Qwen3’s 8B chat model, with thinking and direct-answer modes.
LargeOpen models you can download and run. Pick your memory to see what fits.
Here are the closest that fit 16 GB.
An FP8 edition of Qwen3’s 8B chat model, with thinking and direct-answer modes.
LargeAnswers a written prompt using information from a picture.
LargeA model for working with images and text together.
LargeGenerates text by continuing a written prompt.
LargeGenerates text by continuing a written prompt.
LargeA 4B model dedicated to step-by-step reasoning, with native 256K-token context.
LargeScores how closely a passage matches a search question.
LargeScores how closely a passage matches a search question.
LargeTurns text into number lists for search and meaning comparisons.
LargeA 3.8B instruction model for reasoning and function calling, with 128K-token context.
LargeA 3.8B English instruction model for reasoning and code, with a 4K-token context window.
LargeA 3.8B English instruction model that activates 1.1B parameters per token.
LargeCompares a picture with written labels you supply.
LargeA model for working with images and text together.
LargeA 3B coding model for writing and fixing source code.
LargeA 3B multilingual chat model for writing and structured JSON output.
LargeA 3B chat model with optional reasoning and support for six languages.
LargeAn AWQ edition of a 7B model for writing and fixing code.
MediumA 4-bit edition of a 7B multilingual chat model for writing and structured JSON output.
MediumA 7.8B English and Korean chat model in AWQ, with a 32K-token context window.
MediumA chat model for conversations, questions and writing.
MediumAn FP8 edition of Qwen3’s 4B direct-answer model, with native 256K-token context.
MediumA GGUF fine-tune of Qwen3-8B for coding, reasoning and tool use.
MediumFinds objects in a picture and marks their locations.
MediumWe use one optional cookie to count visits.