Question 1

What does 397B-A17B mean?

Accepted Answer

397B total parameters with 17B activated per token. It is a sparse Mixture-of-Experts model: each MoE layer holds 512 experts but routes each token through only 10 routed plus 1 shared expert, so you get large-model quality at a fraction of the per-token compute.

Question 2

Can it process images?

Accepted Answer

Yes. Qwen3.5 is a unified vision-language model with a vision encoder trained by early fusion, and its card reports results on visual reasoning and video benchmarks. Send OpenAI-style multimodal content parts (image_url) in your chat messages.

Question 3

What context window does it support?

Accepted Answer

262,144 tokens natively, extensible up to 1,010,000 per the model card. The chute's default max_tokens is 1,024; the card recommends 32,768-token outputs for most queries and up to 81,920 for hard math and coding.

Question 4

What sampling settings should I use?

Accepted Answer

For thinking mode: temperature 0.6, top_p 0.95, top_k 20, min_p 0 (also the generation_config.json defaults). For non-thinking mode: temperature 0.7, top_p 0.8, top_k 20. presence_penalty between 0 and 2 reduces endless repetition, at some risk of language mixing.

Question 5

Can I use it commercially?

Accepted Answer

Yes. The model is released under the Apache-2.0 license, which permits commercial use, modification, and redistribution.

Question 6

What does the TEE suffix mean?

Accepted Answer

TEE stands for Trusted Execution Environment. Inference runs inside attested confidential-compute hardware, so your prompts and the model's outputs are processed within a hardware-isolated enclave rather than on an open host.

Question 7

How do I call it from the OpenAI SDK?

Accepted Answer

Set base_url to https://llm.chutes.ai/v1 with your Chutes API key and model to Qwen/Qwen3.5-397B-A17B-TEE. Chat completions, raw completions, and streaming work through the standard SDK methods.

Question 8

Should I keep thinking content in multi-turn history?

Accepted Answer

No. The model card's best practices say historical turns should contain only the final output, not the thinking content. The official chat template handles this automatically; if you manage history yourself, strip reasoning blocks before resending.

Qwen3.5 397B A17B

Sign in to use the playground

Qwen3.5 397B A17B

Sign in to use the playground