ST

StartLux-Decision-v1.1-0.8B-Instant

StartluxGGUF by startlux-modelsUpdated 2026-10-14
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.5 GB
Quick answer

StartLux-Decision-v1.1-0.8B-Instant needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.5 GB (Q4_K_M) to 0.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

StartLux-Decision v1.1 0.8B Instant – fast, non‑text‑generation decision model

StartLux-Decision v1.1 0.8B Instant is a 0.8B parameter decision model built on the qwen35 architecture. It accepts a state (text or JSON with up to 8 images) and typed questions, returning probabilities for each option in a single forward pass. The model is available in GGUF format for llama.cpp.

Good at

  • Fast single‑pass decision making
  • Handles up to 8 images per state
  • Compatible with System One API

Limits

  • No text generation
  • Requires separate vision encoder
  • License cc‑by‑nc‑4.0

Best for

  • Rapid decision support in applications
  • Embedded systems with limited VRAM
  • Batch inference of many decision queries

Who it’s for. Developers building decision‑making services that need quick, non‑text outputs. The model is suited for applications where a single forward pass is sufficient and where image inputs are optional.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q8_00.8 GB 1.7 GB
Fits Get file →

For 8 k context, the Q4_K_M file (0.53 GB) uses about 1.4 GB of VRAM, while the Q8_0 file (0.81 GB) uses about 1.7 GB. Choose Q4_K_M for tighter memory budgets and Q8_0 for higher accuracy. Both are approximate estimates.

What GPU do you need for StartLux-Decision-v1.1-0.8B-Instant?

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 Q8_0 (0.8 GB file, about 1.7 GB in use).

Which StartLux-Decision-v1.1-0.8B-Instant quant should you choose?

Q4_K_M is the usual starting point for StartLux-Decision-v1.1-0.8B-Instant: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 GB, about 1.5 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

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

Frequently asked questions about StartLux-Decision-v1.1-0.8B-Instant

How much VRAM does StartLux-Decision-v1.1-0.8B-Instant need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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-v1.1-0.8B-Instant on an 8 GB GPU?

Yes, with Q8_0: the 0.8 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of StartLux-Decision-v1.1-0.8B-Instant GGUF?

It depends on the quant: Q4_K_M is 0.5 GB, Q8_0 is 0.8 GB.

What context length does StartLux-Decision-v1.1-0.8B-Instant 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-v1.1-0.8B-Instant GGUF?

The files are on Hugging Face in the startlux-models/StartLux-Decision-v1.1-0.8B-Instant-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-v1.1-0.8B-Instant 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 4 GB VRAM?

The Q4_K_M quant requires about 1.4 GB at 8 k context, so 4 GB VRAM is sufficient. The Q8_0 quant needs about 1.7 GB, also within 4 GB.

Does the model support text generation?

No. It returns probabilities for options without generating text.

Is a separate vision encoder needed?

Yes, the mmproj-StartLux-Decision-v1.1-0.8B-Instant-F16.gguf file (205 MB) is required for image inputs.

Similar models

Browse all →

More from startlux-models

All by startlux-models →

More Startlux models

All Startlux →

Other tiny models

All tiny models →