Model reference · open weights
Qwen3-VL is an open-weight language model from unsloth, 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
[!NOTE] Includes Unsloth chat template fixes! - Fine-tune Qwen3-VL-8B for free using our Google Colab notebook - Or train Qwen3-VL with reinforcement learning (GSPO) with our free notebook. - View the rest of our notebooks in our docs here. Qwen3-VL-4B-Instruct Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities. Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on‑demand deployment. Key Enhancements: Visual Agent: Operates PC/mobile GUIs—recognizes elements, understands functions, invokes tools, completes tasks. Visual Coding Boost: Generates Draw.io/HTML/CSS/JS from images/videos. Advanced Spatial Perception: Judges object positions, viewpoints, and occlusions; provides stronger 2D grounding and enables 3D grounding for spatial reasoning and embodied AI. Long Context & Video Understanding: Native 256K context, expandable to 1M; handles books and hours-long video with full recall and second-level indexing. Enhanced Multimodal Reasoning: Excels in STEM/Math—causal analysis and logical, evidence-based answers. Upgraded Visual Recognition: Broader, higher-quality pretraining is able to “recognize everything”—celebrities, anime, products, landmarks, flora/fauna, etc. Expanded OCR: Supports 32 languages (up from 19); robust in low light, blur, and tilt; better with rare/ancient characters and jargon; improved long-document structure parsing. Text Understanding on par with pure LLMs: Seamless text–vision fusion for lossless, unified comprehension. Model Architecture Updates: 1. Interleaved-MRoPE: Full‑frequency allocation over time, width, and height via robust positional embeddings, enhancing long‑horizon video reasoning. 2. DeepStack: Fuses multi‑level ViT features to capture fine‑grained details and sharpen image–text alignment. 3. Text–Timestamp Alignment: Moves beyond T‑RoPE to pr
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | unsloth |
|---|---|
| Type | Language models |
| Variants | 1 |
| Runs with | transformers |
| Based on | Qwen/Qwen3-VL-4B-Instruct |
| Released | 2025-10-30 |
| Popularity | 334k downloads / month |
| Likes | 72 |
| 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.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Qwen3-VL-4B-Instruct-GGUF | — | GGUF | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys unsloth-qwen3-vl for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (unsloth-qwen3-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":"unsloth-qwen3-vl","messages":[{"role":"user","content":"Hello"}]}'
Details
Tags
Papers
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗