Qwen3.5 is a reasoning vision-language model that supports tool use. With 35B total parameters and 3B activated, it outperforms previous generation models more than 6x its size.

MODEL

Forked from qwen/qwen3.5-35b-a3b•Updated on April 15

kristianlom

@kristianlom

Joined April 2026

@kristianlom

Projects

qwen35-35b-a3b

Public

Qwen3.5 is a reasoning vision-language model that supports tool use. With 35B total parameters and 3B activated, it outperforms previous generation models more than 6x its size.

MODEL

Forked from qwen/qwen3.5-35b-a3b•Updated on April 15

gemma-4-31b

Public

31B dense Gemma4 variant. Supports vision input, reasoning, and tool calls.

MODEL

Forked from google/gemma-4-31b•Updated on April 15

gemma-4-31b

Public

31B dense Gemma4 variant. Supports vision input, reasoning, and tool calls.

MODEL

Forked from google/gemma-4-31b•Updated on April 15