ProcObject Qwen3 VL 4B needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 1.7 GB (Q2_K) to 8.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
ProcObject Qwen3 VL 4B – 4B‑parameter vision‑language model fine‑tuned for object‑centric video QA
ProcObject Qwen3 VL 4B is a 4.02‑billion‑parameter model based on Qwen3‑VL. It is fine‑tuned with object‑centric SFT on ProcObject‑10K for answering questions about objects in instructional videos and localizing supporting moments. The model runs with standard Qwen3‑VL inference cost.
Good at
- Object‑centric video QA
- Vision‑based evidence localization
- Instructional video analysis
Limits
- cc‑by‑nc‑4.0 license
- No extra inference cost for auxiliary heads
- Trained on 262144 context tokens
Best for
- Developing instructional video assistants
- Researching object‑centric video understanding
- Creating evidence‑based QA systems
Who it’s for. Researchers and developers who need a vision‑language model capable of answering object‑centric questions in instructional videos. The model is suitable for academic projects, prototype development, and educational tools that require video‑based reasoning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.7 GB | 3.4 GB | Fits | Get file → | |
| Q3_K_S | 1.9 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_M | 2.1 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_L | 2.2 GB | 3.9 GB | Fits | Get file → | |
| IQ4_XS | 2.3 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q5_K_S | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q5_K_M | 2.9 GB | 4.6 GB | Fits | Get file → | |
| Q6_K | 3.3 GB | 5.0 GB | Fits | Get file → | |
| Q8_0 | 4.3 GB | 6.0 GB | Fits | Get file → | |
| F16 | 8.1 GB | 9.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (est. 4.2 GB memory at 8 k context). If 4 GB VRAM is available, Q3_K_M (3.8 GB) or Q2_K (3.4 GB) are good choices. For larger budgets, Q5_K_M (4.6 GB) or Q6_K (5 GB) provide higher quality.
What GPU do you need for ProcObject Qwen3 VL 4B?
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: the best quant that fits is IQ4_XS (2.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.1 GB file, about 9.8 GB in use).
Which ProcObject Qwen3 VL 4B quant should you choose?
Q4_K_M is the usual starting point for ProcObject Qwen3 VL 4B: it balances file size and quality well. Here it is a 2.5 GB file.
The Q8_0 file is 4.3 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 Q2_K at 1.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ProcObject Qwen3 VL 4B
How much VRAM does ProcObject Qwen3 VL 4B need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 ProcObject Qwen3 VL 4B on an 8 GB GPU?
Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ProcObject Qwen3 VL 4B GGUF?
It depends on the quant: Q2_K is 1.7 GB, Q3_K_S is 1.9 GB, Q3_K_M is 2.1 GB, Q3_K_L is 2.2 GB, IQ4_XS is 2.3 GB, Q4_K_S is 2.4 GB and 6 more.
What context length does ProcObject Qwen3 VL 4B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). 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 ProcObject Qwen3 VL 4B GGUF?
The files are on Hugging Face in the mradermacher/ProcObject-Qwen3-VL-4B-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 ProcObject Qwen3 VL 4B use?
Hugging Face lists the license as cc-by-nc-4.0. 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 4.2 GB memory at 8 k context, fitting comfortably on 8 GB VRAM.
Does it support vision?
Yes, the model has vision capabilities and is fine‑tuned for object‑centric video tasks.
What license does it use?
The model is released under a cc‑by‑nc‑4.0 license.