Model reference · open weights
Step3-VL is an open-weight language model from stepfun-ai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
[](https://huggingface.co/collections/stepfun-ai/step3-vl-10b) [](https://modelscope.cn/collections/stepfun-ai/Step3-VL-10B) [](https://arxiv.org/abs/2601.09668) []() 📢 News & Updates - 🚀 Online Demo: Explore Step3-VL-10B on Hugging Face Spaces ! - 📢 [Notice] FP8 Quantization Support : FP8 quantized weights are now available. (Download link) - 📢 [Notice] vLLM Support: vLLM integration is now officially supported! (PR #32329) - ✅ [Fixed] HF Inference: Resolved the eostokenid misconfiguration in config.json that caused infinite generation loops. (PR #abdf3) - ✅ [Fixing] Metric Correction: We sincerely apologize for inaccuracies in the Qwen3VL-8B benchmarks (e.g., AIME, HMMT, LCB). The errors were caused by an incorrect maxtokens setting (mistakenly set to 32k) during our large-scale evaluation process. We are re-running the tests and will provide corrected numbers in the next version of technical report. 🚀 Introduction STEP3-VL-10B is a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. Despite its compact 10B parameter footprint, STEP3-VL-10B excels in visual perception, complex reasoning, and human-centric alignment. It consistently outperforms models under the 10B scale and rivals or surpasses significantly larger open-weights models (10×–20× its size), such as GLM-4.6V (106B-A12B), Qwen3-VL-Thinking (235B-A22B), and top-tier proprietary flagships like Gemini 2.5 Pro and Seed-1.5-VL. The success of STEP3-VL-10B is driven by two key strategic designs: 1. Unified Pre-training on High-Quality Multimodal Corpus: A single-stage, fully unfrozen training strategy on a 1.2T token multimodal corpus, focusing on two foundational capabilities: reasoning (e.g., general knowledge and education-centric tasks) and perception (e.g., grounding, counting, OCR, and GUI interactions). By jointly optimizing the Perception Encoder and the Qwen3-8B decoder, STEP3-VL-10B establishes intrinsic vision-language synergy. 2. Scaled Multimodal Reinforcement Learning and Parallel Reasoning: Frontier capabilities are unlocked through a rigorous post-training pipeline comprising two-stage supervised
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | stepfun-ai |
|---|---|
| Type | Language models |
| Parameters (lead) | 10.2B |
| Variants | 2 |
| Based on | stepfun-ai/Step3-VL-10B-Base |
| Released | 2026-01-13 |
| Popularity | 40k downloads / month |
| Likes | 414 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Using it via the API
Once AxForge deploys step3-vl for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (step3-vl below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"step3-vl","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗