StartLux Decision v1 2B BF16 needs about 4.7 GB of memory at BF16 (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
StartLux Decision v1 2B BF16 – a decision‑making LLM with vision support
StartLux Decision v1 2B BF16 is a 1.88 B parameter model built on the qwen35 architecture. It answers typed questions about states, including text, JSON or images, up to 262,144 tokens. The model returns probabilities for each option and is optimized for fast inference with llama.cpp.
Good at
- Fast decision inference
- Supports images and long inputs
- Provides probability scores
Limits
- Requires BF16 quantization
- Needs recent llama.cpp (build b10454+)
- CC BY‑NC 4.0 license – no commercial use without separate license
Best for
- Rapid decision pipelines
- Batch question answering
- Vision‑enabled state evaluation
Who it’s for. Researchers and developers needing a lightweight decision model that can process large contexts and images. The model is suitable for non‑commercial projects that require fast, probabilistic decisions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 3.8 GB | 4.7 GB | Fits | Get file → |
The only available quant is BF16, 3.78 GB file size. It requires about 4.7 GB VRAM at 8 k context. For 8 GB VRAM, BF16 is the recommended quant. No other quantizations are provided.
What GPU do you need for StartLux Decision v1 2B BF16?
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 BF16 (3.8 GB file, about 4.7 GB in use).
Which StartLux Decision v1 2B BF16 quant should you choose?
BF16 (3.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about StartLux Decision v1 2B BF16
How much VRAM does StartLux Decision v1 2B BF16 need?
About 4.7 GB at BF16 with an 8K context window. That is the 3.8 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 StartLux Decision v1 2B BF16 on an 8 GB GPU?
Yes, with BF16: the 3.8 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of StartLux Decision v1 2B BF16 GGUF?
It depends on the quant: BF16 is 3.8 GB.
What context length does StartLux Decision v1 2B BF16 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download StartLux Decision v1 2B BF16 GGUF?
The files are on Hugging Face in the startlux-models/StartLux-Decision-v1-2B-BF16-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 StartLux Decision v1 2B BF16 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, BF16 requires approximately 4.7 GB VRAM at 8 k context, which fits within an 8 GB GPU.
Does the model support vision inputs?
Yes, the weights include a vision tower and the inference package accepts images as evidence.
Is the model free for commercial use?
No, the model is CC BY‑NC 4.0. Commercial use requires a separate license from StartLux Labs.