StepFunStep 3 VL 10B
Step 3 VL 10B is a 10-billion-parameter open-source multimodal chat model built by StepFun. It processes text and image inputs with a 65,536-token context window.
Input
Output
Context
66K
Max Output
-
Parameters
10.2B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Benchmarks
Estimated GPU requirements for Step 3 VL 10B
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 StepFun
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 Step 3 VL 10B
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Step 3 VL 10B advertises a context window of 65,536 tokens. 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. Step 3 VL 10B 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.
Step 3 VL 10B 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.
Step 3 VL 10B 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 Step 3 VL 10B is shown as not available rather than estimated.
Not on the managed pool today; Step 3 VL 10B is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
About 10.5 GB at INT8 for the weights and a default context, from the catalog's 10.2B 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 4, 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.