Parcourir les modèles

An FP8 edition of Qwen3’s 8B chat model, with thinking and direct-answer modes.

Generates text by continuing a written prompt.

Generates text by continuing a written prompt.

A 4B model dedicated to step-by-step reasoning, with native 256K-token context.

Scores how closely a passage matches a search question.

A 3.8B instruction model for reasoning and function calling, with 128K-token context.

A 3.8B instruction model for code and reasoning, with a 128K-token context window.

A 3.8B English instruction model for reasoning and code, with a 4K-token context window.

A 3.8B English instruction model that activates 1.1B parameters per token.

Compares a picture with written labels you supply.

Turns text into number lists for search and meaning comparisons.

An 11B chat model optimized for Polish, quantized with AWQ.

A 3B coding model for writing and fixing source code.

Scores how closely a passage matches a search question.

A 3B chat model with optional reasoning and support for six languages.

An AWQ edition of Qwen3’s 8B chat model, with thinking and direct-answer modes.

An AWQ edition of a 7B model for writing and fixing code.

A GPTQ edition of a 7B model for writing and fixing code.

A 4-bit edition of a 7B multilingual chat model for writing and structured JSON output.

An FP8 edition of Qwen3’s 4B direct-answer model, with native 256K-token context.

An 8B mixture-of-experts chat model in GGUF, with 1.5B active parameters.

Finds objects in a picture and marks their locations.

Turns recorded speech into written text.

Compares a picture with written labels you supply.