Step3 VL 10B needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 4.1 GB (Q3_K_M) to 16.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Step3 VL 10B – 8.19B‑parameter multimodal model
Step3 VL 10B is a 8.19B‑parameter model built on the Qwen3 architecture. It supports reasoning, tools, and vision tasks. The model is released under the apache-2.0 license and offers a 40960‑token context window.
Good at
- Vision‑aware reasoning
- Tool‑use integration
- Multimodal alignment
Limits
- No vision support in older quantizations
- Large VRAM requirement for high‑quality quant
- No explicit language list
Best for
- Image‑captioning with reasoning
- Multimodal question answering
- Tool‑augmented dialogue
Who it’s for. Developers building multimodal applications who need a compact yet capable foundation model. The model is suitable for open‑source projects requiring a balance between performance and resource usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 4.1 GB | 5.8 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 6.7 GB | Fits | Get file → | |
| Q6_K | 6.7 GB | 8.4 GB | Too big | Get file → | |
| Q8_0 | 8.7 GB | 10.4 GB | Too big | Get file → | |
| BF16 | 16.4 GB | 18.1 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (5.8 GB estimate). For 12 GB VRAM use Q6_K (8.4 GB estimate). For 16 GB VRAM use Q8_0 (10.4 GB estimate). Estimates are approximate and based on 8 k context size.
What GPU do you need for Step3 VL 10B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q3_K_M (4.1 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (5.0 GB file, about 6.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.4 GB file, about 18.1 GB in use).
Which Step3 VL 10B quant should you choose?
Q4_K_M is the usual starting point for Step3 VL 10B: it balances file size and quality well. Here it is a 5.0 GB file.
The Q8_0 file is 8.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q3_K_M at 4.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Step3 VL 10B
How much VRAM does Step3 VL 10B need?
About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Step3 VL 10B on an 8 GB GPU?
Yes, with Q4_K_M: the 5.0 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Step3 VL 10B GGUF?
It depends on the quant: Q3_K_M is 4.1 GB, Q4_K_M is 5.0 GB, Q6_K is 6.7 GB, Q8_0 is 8.7 GB, BF16 is 16.4 GB.
What context length does Step3 VL 10B support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Step3 VL 10B GGUF?
The files are on Hugging Face in the JamePeng2023/Step3-VL-10B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Step3 VL 10B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Step3 VL 10B on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 5.8 GB of VRAM at 8 k context, fitting within an 8 GB GPU.
What quantization gives the best quality?
The BF16 quant provides the highest quality but requires about 18.1 GB of VRAM at 8 k context.
Is the model vision‑capable?
Yes, the model has detected vision ability and supports multimodal inputs.