QwenQwen 3.5 397B A17B
Qwen develops the Qwen 3.5 397B A 17B model, a chat model that excels at tasks such as code generation, reasoning, and text generation, with a notable strength in multimodal understanding thanks to its unified vision-language foundation. Its efficient hybrid architecture, combining Gated Delta Networks and sparse Mixture-of-Experts, enables high-throughput inference with minimal latency.
Input
Output
Context
262K
Max Output
66K
Parameters
397B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Served variants
The same model in other encodings or serving configurations. Requesting qwen3-5-397b-a17b lets routing pick among them; the ids below pin one build.
qwen3-5-397b-a17b:fp8quantized
Benchmarks
Resources & Links
Estimated GPU requirements for Qwen 3.5 397B A17B
Estimates based on INT8 quantization at up to 32K context. A count above one assumes tensor parallelism across the cards. Actual requirements vary by framework and configuration.
More models by Qwen
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Qwen 3.5 397B A17B
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Qwen 3.5 397B A17B advertises a context window of 262,144 tokens, with a maximum output of 66,000 tokens in a single response. The figure is the creator's published maximum; a given provider may serve less, and the gateway routes on what each provider actually serves.
Yes. Qwen 3.5 397B A17B is an open-weight model released under the Apache 2.0 license, so the weights can be downloaded and self-hosted within that license's terms.
Qwen 3.5 397B A17B accepts Text and Image and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
Qwen 3.5 397B A17B has published results from Artificial Analysis, shown by suite in the benchmarks card above exactly as the publisher reported them. Scores are not combined across suites, and a suite that has not measured Qwen 3.5 397B A17B is shown as not available rather than estimated.
Yes. Qwen 3.5 397B A17B is served on the managed pool through the OpenAI-compatible endpoint as qwen3-5-397b-a17b, pinned by name or chosen by routing when it is the best fit for a request. The Try in Playground button opens it directly.
About 390.1 GB at INT8 for the weights and a default context, from the catalog's 397B parameter count; FP16 needs roughly twice that, and long contexts or many concurrent requests add KV cache on top. The GPU section on this page lists cards that hold it, and the capacity planner sizes it for your context length and traffic.
Fields collected from public registries, provider APIs and benchmark publishers, each tagged with its source.
Last updated: Nov 6, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start on the free plan with 5,000 requests a month, no card required.