Code As World VL 9B needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 11 quants, from 4.3 GB (Q3_K_S) to 17.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Code As World VL 9B – a vision‑language model for physical reasoning
Code As World VL 9B is a 8.95 billion‑parameter model based on Qwen3.5‑9B. It is fine‑tuned for physical understanding and quantitative reasoning over videos. The model accepts 16‑frame video input and has a 4,608‑token maximum context length.
Good at
- Vision‑language reasoning
- Physical measurement tasks
- Video‑based quantitative analysis
Limits
- No general chat capability
- Requires 16‑frame video input
- Outputs may be inaccurate
Best for
- Research on physical understanding
- Quantitative reasoning from images
- Video analysis in controlled settings
Who it’s for. Researchers and developers needing a vision‑language model focused on physical reasoning. The model is not intended for general conversation or safety‑critical applications without independent verification.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 4.3 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 4.6 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q4_0 | 5.3 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_S | 5.4 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q5_0 | 6.3 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_S | 6.3 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_M | 6.5 GB | 8.0 GB | Too big | Get file → | |
| BF16 | 17.9 GB | 19.5 GB | Too big | Get file → | |
| F16 | 17.9 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (5.63 GB file, ~7.2 GB memory at 8k context). For 12 GB VRAM use Q5_K_M (6.47 GB file, ~8 GB memory). For larger budgets, F16 or BF16 provide full precision but require ~19.5 GB memory.
What GPU do you need for Code As World VL 9B?
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_S (4.3 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (6.5 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (6.5 GB file, about 8.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (6.5 GB file, about 8.0 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 19.5 GB in use).
Which Code As World VL 9B quant should you choose?
Q4_K_M is the usual starting point for Code As World VL 9B: it balances file size and quality well. Here it is a 5.6 GB file.
If memory is tight, the smallest file is Q3_K_S at 4.3 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 Code As World VL 9B
How much VRAM does Code As World VL 9B need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Code As World VL 9B on an 8 GB GPU?
Yes, with Q5_K_M: the 6.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Code As World VL 9B GGUF?
It depends on the quant: Q3_K_S is 4.3 GB, Q3_K_M is 4.6 GB, Q3_K_L is 4.9 GB, Q4_0 is 5.3 GB, Q4_K_S is 5.4 GB, Q4_K_M is 5.6 GB and 5 more.
What context length does Code As World VL 9B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Code As World VL 9B GGUF?
The files are on Hugging Face in the prithivMLmods/Code-as-World-VL-9B-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 Code As World VL 9B 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 Code As World VL 9B on 8 GB VRAM?
Yes, using the Q4_K_M quantized file which uses about 7.2 GB of VRAM at 8k context.
Does the model support text‑only input?
No, it is designed for 16‑frame video input and does not handle text‑only queries effectively.
What license applies to this model?
The model is released under the Apache‑2.0 license and inherits the base model’s license terms.