Runtime is almost here: join TypeSafe AI, Cognition, DoorDash and more in SF. Limited seats left. Register now

Qwen3.5 9B

Qwen3.5 9B is the largest of the four small dense models in Qwen's natively multimodal Qwen3.5 family: a 9B-parameter vision-language model with thinking mode on by default, a 262K-token context extensible to 1M with YaRN, 201-language coverage, and open weights under Apache 2.0.

Model

Qwen3.5 9B is a 32-layer causal language model with a vision encoder, trained with early text-vision fusion so it handles text and images natively. Its hybrid layout repeats eight blocks of three Gated DeltaNet linear-attention layers followed by one gated full-attention layer, for high-throughput, low-latency inference across a native 262,144-token context that can be extended to 1,010,000 tokens with YaRN scaling. The model uses a 4096-dimensional hidden state, a 248K-token vocabulary, and multi-token prediction training. It thinks by default, emitting reasoning inside think tags before answering, and can be switched to direct instruct-style responses. It supports tool calling and 201 languages and dialects.

This is the post-trained model, fine-tuned from Qwen3.5-9B-Base. Qwen benchmarks it against GPT-OSS-120B, GPT-OSS-20B, Qwen3-Next-80B-A3B-Thinking, and Qwen3-VL-30B-A3B on language and vision tasks, and recommends a 32,768-token output budget for most queries. Weights are released under the Apache 2.0 license. Full details are in Qwen's announcement and the model card.

Dedicated Endpoint

Docs

A Dedicated Endpoint is your own deployment of Qwen3.5 9B, on an inference stack that Modal tunes and autoscales. Bring fine-tuned weights if you have them. Compute is billed by the second, and only while it runs.

$ modal endpoint create --model Qwen/Qwen3.5-9B

Related resources

Ship your first app in minutes.

Get Started

$30 / month free compute