Youtu-VL-4B-Instruct needs about 4.3 GB of memory at Q4_K_M (a 3.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 37 quants, from 0.0 GB to 9.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.9 GB.
Youtu-VL-4B-Instruct – a 4.9B parameter vision‑language model
Youtu-VL-4B-Instruct is a 4.9B parameter VLM built on the Youtu‑LLM architecture. It supports vision tasks such as image classification, object detection, and segmentation. The model is available in multiple GGUF quantizations.
Good at
- Vision‑centric tasks
- Multimodal understanding
- Efficient inference
Limits
- No text‑only usage
- Requires GPU with at least 8 GB VRAM for higher quantizations
- License is other
Best for
- Image classification in edge devices
- Object detection in small‑scale projects
- Multimodal chat with visual input
Who it’s for. Developers building lightweight vision‑language applications who need a compact model with good visual performance. The model is suitable for research and production environments that can run GGUF files on llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.2 GB | Fits | Get file → | |
| Q2_K_S | 2.2 GB | 3.4 GB | Fits | Get file → | |
| Q2_K_M | 2.3 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XXS | 2.3 GB | 3.5 GB | Fits | Get file → | |
| IQ2_XS | 2.3 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XS | 2.4 GB | 3.6 GB | Fits | Get file → | |
| IQ2_S | 2.4 GB | 3.6 GB | Fits | Get file → | |
| IQ2_M | 2.4 GB | 3.6 GB | Fits | Get file → | |
| IQ3_M | 2.5 GB | 3.7 GB | Fits | Get file → | |
| IQ3_S | 2.5 GB | 3.7 GB | Fits | Get file → | |
| Q2_K_L | 2.5 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_S | 2.7 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_M | 2.8 GB | 4.0 GB | Fits | Get file → | |
| Q4_0 | 2.8 GB | 4.0 GB | Fits | Get file → | |
| IQ4_XS | 2.8 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_L | 2.9 GB | 4.1 GB | Fits | Get file → | |
| IQ4_NL | 3.0 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_S | 3.1 GB | 4.3 GB | Fits | Get file → | |
| Q4_1 | 3.1 GB | 4.3 GB | Fits | Get file → | |
| Q4_0 | 3.1 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_M | 3.1 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_L | 3.3 GB | 4.5 GB | Fits | Get file → | |
| Q5_0 | 3.4 GB | 4.6 GB | Fits | Get file → | |
| Q4_1 | 3.4 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_S | 3.6 GB | 4.8 GB | Fits | Get file → | |
| Q5_K_M | 3.6 GB | 4.8 GB | Fits | Get file → | |
| Q5_0 | 3.6 GB | 4.9 GB | Fits | Get file → | |
| Q5_1 | 3.7 GB | 4.9 GB | Fits | Get file → | |
| Q5_K_L | 3.8 GB | 5.0 GB | Fits | Get file → | |
| Q5_1 | 3.9 GB | 5.1 GB | Fits | Get file → | |
| Q6_K_M | 4.0 GB | 5.3 GB | Fits | Get file → | |
| Q6_K_L | 4.2 GB | 5.4 GB | Fits | Get file → | |
| Q8_0 | 5.2 GB | 6.4 GB | Fits | Get file → | |
| BF16 | 7.2 GB | 8.4 GB | Too big | Get file → | |
| F16 | 7.2 GB | 8.4 GB | Too big | Get file → | |
| BF16 | 9.8 GB | 11.0 GB | Too big | Get file → | |
| F16 | 9.8 GB | 11.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 3.13 GB, memory 4.3 GB). If 6 GB VRAM is available, Q3_K_M (2.76 GB, 4 GB memory) is a good choice. For 4 GB VRAM, Q2_K_S (2.21 GB, 3.4 GB memory) is recommended.
What GPU do you need for Youtu-VL-4B-Instruct?
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 (2.8 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K_L (4.2 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.2 GB file, about 6.4 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (9.8 GB file, about 11.0 GB in use).
Which Youtu-VL-4B-Instruct quant should you choose?
Q4_K_M is the usual starting point for Youtu-VL-4B-Instruct: it balances file size and quality well. Here it is a 3.1 GB file.
The Q8_0 file is 5.2 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Youtu-VL-4B-Instruct
How much VRAM does Youtu-VL-4B-Instruct need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 3.1 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 Youtu-VL-4B-Instruct on an 8 GB GPU?
Yes, with Q8_0: the 5.2 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Youtu-VL-4B-Instruct GGUF?
It depends on the quant: file is 0.0 GB, Q2_K_S is 2.2 GB, Q2_K_M is 2.3 GB, IQ3_XXS is 2.3 GB, IQ2_XS is 2.3 GB, IQ3_XS is 2.4 GB and 31 more.
What context length does Youtu-VL-4B-Instruct support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.9 GB at 32K.
Where can I download Youtu-VL-4B-Instruct GGUF?
The files are on Hugging Face in the Mungert/Youtu-VL-4B-Instruct-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 Youtu-VL-4B-Instruct use?
Hugging Face lists the license as other. 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 Youtu-VL-4B-Instruct on 8 GB VRAM?
Yes, the Q4_0 quantization requires about 4.3 GB VRAM at 8 k context, which fits in 8 GB VRAM.
Does the model support text‑only inference?
No, the model is vision‑centric and requires image input for its intended tasks.
What is the smallest quantization I can use?
The smallest quantization listed is unknown (0.01 GB), but its memory usage is 1.2 GB at 8 k context.