Decision 2.0 Lux 9B needs about 6.6 GB of memory at Q4_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 5.1 GB (Q4_K_M) to 15.9 GB (BF16).
Decision 2.0 Lux 9B – a 9B decision‑making model
Decision 2.0 Lux 9B is a 7.94 billion‑parameter model built on the qwen35 architecture. It excels at reasoning and tool usage, returning probabilities for multiple choice, yes/no, and score questions in a single forward pass. The model is licensed under Apache‑2.0.
Good at
- Fast single‑question inference
- Multi‑question one‑pass responses
- Probability‑based decision outputs
Limits
- No vision support
- Requires Decision 2.0 runtime
- Limited to 16384 context tokens
Best for
- Rapid decision‑making APIs
- Batch question answering
- Probability‑driven analytics
Who it’s for. Developers building decision‑oriented services that need quick, probability‑based answers. The model is suitable for applications requiring multiple question types answered together without text generation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.1 GB | 6.6 GB | Fits | Get file → | |
| Q8_0 | 8.5 GB | 10.0 GB | Too big | Get file → | |
| BF16 | 15.9 GB | 17.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 5.07 GB, estimated 6.6 GB memory). For 12 GB VRAM, Q8_0 (8.46 GB, 10 GB memory) is suitable. BF16 requires 15.9 GB and 17.5 GB memory, best for larger GPUs.
What GPU do you need for Decision 2.0 Lux 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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q4_K_M (5.1 GB file, about 6.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.0 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.9 GB file, about 17.5 GB in use).
Which Decision 2.0 Lux 9B quant should you choose?
Q4_K_M is the usual starting point for Decision 2.0 Lux 9B: it balances file size and quality well. Here it is a 5.1 GB file.
The Q8_0 file is 8.5 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Decision 2.0 Lux 9B
How much VRAM does Decision 2.0 Lux 9B need?
About 6.6 GB at Q4_K_M with an 8K context window. That is the 5.1 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 Decision 2.0 Lux 9B on an 8 GB GPU?
Yes, with Q4_K_M: the 5.1 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Decision 2.0 Lux 9B GGUF?
It depends on the quant: Q4_K_M is 5.1 GB, Q8_0 is 8.5 GB, BF16 is 15.9 GB.
What context length does Decision 2.0 Lux 9B support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.1 GB at 8K and 2.1 GB at 16K.
Where can I download Decision 2.0 Lux 9B GGUF?
The files are on Hugging Face in the vllm-sr/Decision-2.0-Lux-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 Decision 2.0 Lux 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 Decision 2.0 Lux 9B on 8 GB VRAM?
Yes, using the Q4_K_M quantization which uses about 6.6 GB of VRAM at 8K context.
Does the model support image inputs?
No, the model does not include vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.