Explorar modelos

Modelos abertos que você pode baixar e executar. Escolha sua memória para ver o que cabe.

Resultados de modelos

Nada dos primeiros 50 cabe em 16 GB. Estes são os mais próximos que cabem.

Ready

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

Large
Cerca de 13 GB de memóriaConversar e escrever9.44 GBapache-2.0585,833 downloads no catálogo
Ready

Answers a written prompt using information from a picture.

Large
Cerca de 13 GB de memóriaEntender imagens9.32 GBapache-2.08,496,525 downloads no catálogo
ReliquaryForge

qwen3-4B-base-dapo-v4

Ready

Generates text by continuing a written prompt.

Large
Cerca de 11 GB de memóriaConversar e escrever8.04 GBapache-2.0936,257 downloads no catálogo
Ready

A 4B chat model with optional reasoning and support for 100+ languages.

Large
Cerca de 11 GB de memóriaConversar e escrever8.04 GBapache-2.015,512,125 downloads no catálogo
Ready

Generates text by continuing a written prompt.

Large
Cerca de 11 GB de memóriaConversar e escrever8.04 GBapache-2.0664,826 downloads no catálogo

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

Large
Cerca de 11 GB de memóriaConversar e escrever8.04 GBapache-2.0591,768 downloads no catálogo

Scores how closely a passage matches a search question.

Large
Cerca de 11 GB de memóriaRank search results8.04 GBapache-2.01,755,665 downloads no catálogo

Turns text into number lists for search and meaning comparisons.

Large
Cerca de 11 GB de memóriaPesquisar documentos8.04 GBapache-2.02,446,340 downloads no catálogo
Ready

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

Large
Cerca de 10 GB de memóriaConversar e escrever7.67 GBmit619,945 downloads no catálogo
Ready

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

Large
Cerca de 10 GB de memóriaConversar e escrever7.64 GBmit1,162,551 downloads no catálogo
Ready

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

Large
Cerca de 10 GB de memóriaConversar e escrever7.64 GBmit583,425 downloads no catálogo
deepseek-ai

DeepSeek-OCR-2

Ready

A model for working with images and text together.

Large
Cerca de 9 GB de memóriaEntender imagens6.78 GBapache-2.03,202,247 downloads no catálogo

A 3B multilingual chat model for writing and structured JSON output.

Large
Cerca de 9 GB de memóriaConversar e escrever6.17 GBqwen-research-non-commercial5,284,682 downloads no catálogo
HuggingFaceTB

SmolLM3-3B

Ready

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

Large
Cerca de 8 GB de memóriaConversar e escrever6.15 GBapache-2.0663,378 downloads no catálogo
Ready

A 9B reasoning model in GGUF, with tool-calling and coding examples on its model card.

Medium
Cerca de 8 GB de memóriaConversar e escrever5.63 GBmit4,907,682 downloads no catálogo

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

Medium
Cerca de 8 GB de memóriaConversar e escrever5.55 GBapache-2.0604,743 downloads no catálogo

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

Medium
Cerca de 7 GB de memóriaConversar e escrever5.19 GBapache-2.0873,213 downloads no catálogo
Ready

Turns recorded speech into written text.

Medium
Cerca de 7 GB de memóriaTranscrever fala4.7 GBapache-2.01,467,010 downloads no catálogo

A model for working with images and text together.

Medium
Cerca de 6 GB de memóriaEntender imagens4.42 GBapache-2.03,696,917 downloads no catálogo
Ready

A 1.7B chat model with optional reasoning and a native 32K-token context window.

Medium
Cerca de 6 GB de memóriaConversar e escrever4.06 GBapache-2.05,748,993 downloads no catálogo