ST

StartLux Decision v1 0.8B BF16

StartluxGGUF by startlux-modelsUpdated 2026-10-10
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant1.5 GB
Quick answer

StartLux Decision v1 0.8B BF16 needs about 2.4 GB of memory at BF16 (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

StartLux Decision v1 0.8B BF16 – a decision‑making LLM

StartLux Decision v1 0.8B BF16 is a 0.8B‑parameter model built on the qwen35 architecture. It answers typed questions about a state, returning probabilities for each option. The model supports up to 262,144 tokens and includes a vision tower for image evidence.

Good at

  • Fast decision inference
  • Reasoning with tools
  • Large context handling

Limits

  • No commercial use without license
  • No vision support without the inference package
  • Requires recent llama.cpp

Best for

  • Decision‑making APIs
  • Batch question processing
  • Research on typed decision tasks

Who it’s for. Researchers and developers needing a lightweight decision model for typed question answering. The model is free for non‑commercial use under CC BY‑NC 4.0, but commercial use requires a separate license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF161.5 GB 2.4 GB
Fits Get file →

The BF16 GGUF file is 1.52 GB and needs about 2.4 GB of VRAM at 8 k context. This is the only quant available. For lower VRAM, a different quant would be required, but none are provided.

What GPU do you need for StartLux Decision v1 0.8B 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: the best quant that fits is BF16 (1.5 GB file, about 2.4 GB in use).

Which StartLux Decision v1 0.8B BF16 quant should you choose?

BF16 (1.5 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

Architectureqwen35
Parameters752M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized bystartlux-models
FamilyStartlux
Downloads (HF)143
Last updated2026-10-10

Frequently asked questions about StartLux Decision v1 0.8B BF16

How much VRAM does StartLux Decision v1 0.8B BF16 need?

About 2.4 GB at BF16 with an 8K context window. That is the 1.5 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 StartLux Decision v1 0.8B BF16 on an 8 GB GPU?

Yes, with BF16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of StartLux Decision v1 0.8B BF16 GGUF?

It depends on the quant: BF16 is 1.5 GB.

What context length does StartLux Decision v1 0.8B 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 0.8B BF16 GGUF?

The files are on Hugging Face in the startlux-models/StartLux-Decision-v1-0.8B-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 0.8B 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 StartLux Decision v1 0.8B BF16 on 8 GB VRAM?

Yes, the model requires about 2.4 GB of VRAM at 8 k context, so 8 GB is sufficient.

Does the model support image inputs?

Yes, the weights include a vision tower and the inference package can process images as evidence.

Is commercial use allowed?

No, commercial use requires a separate license from StartLux Labs; the model is free for non‑commercial research under CC BY‑NC 4.0.

Other GGUFs of StartLux-Decision-v1-0.8B

Similar models

Browse all →

More from startlux-models

All by startlux-models →

More Startlux models

All Startlux →

Other tiny models

All tiny models →