ED

Edceleste Decider 0.8b

EdcelesteGGUF by mradermacherUpdated 2026-10-08
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.4 GB
Quick answer

Edceleste Decider 0.8b 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 12 quants, from 0.4 GB (Q2_K) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Edceleste Decider 0.8b – a fine‑tuned Qwen35 model for Elite Dangerous copilot tasks

Edceleste Decider 0.8b is a 0.752 billion‑parameter Qwen35 model fine‑tuned for Elite Dangerous. It answers system‑one questions about game‑state projection and bound ship actions. The model is released under Apache‑2.0 and supports reasoning and tools.

Good at

  • Reasoning on game‑state queries
  • Selecting bound ship actions
  • Determining LLM necessity

Limits

  • No vision support
  • Trained context 262144 tokens
  • Requires at least 1.3 GB VRAM for 8 k context

Best for

  • Elite Dangerous copilot scripts
  • Game‑state decision support
  • Automated action selection

Who it’s for. Developers building Elite Dangerous assistants or bots. Researchers needing a lightweight Qwen35 variant for game‑specific reasoning tasks. Users who prefer an Apache‑2.0 licensed model with a small footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.4 GB 1.3 GB
Fits Get file →
Q3_K_S0.4 GB 1.3 GB
Fits Get file →
Q3_K_M0.5 GB 1.4 GB
Fits Get file →
Q3_K_L0.5 GB 1.4 GB
Fits Get file →
Q4_K_S0.5 GB 1.4 GB
Fits Get file →
IQ4_XS0.5 GB 1.4 GB
Fits Get file →
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q5_K_S0.6 GB 1.5 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q6_K0.6 GB 1.5 GB
Fits Get file →
Q8_00.8 GB 1.7 GB
Fits Get file →
F161.5 GB 2.4 GB
Fits Get file →

For 8 GB VRAM, Q2_K (0.42 GB, 1.3 GB memory) or Q3_K_S (0.44 GB, 1.3 GB memory) are suitable. If 12 GB VRAM is available, Q4_K_M (0.53 GB, 1.4 GB memory) offers a balance of size and quality. For maximum precision, use Q8_0 (0.81 GB, 1.7 GB memory) or F16 (1.52 GB, 2.4 GB memory).

What GPU do you need for Edceleste Decider 0.8b?

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 F16 (1.5 GB file, about 2.4 GB in use).

Which Edceleste Decider 0.8b quant should you choose?

Q4_K_M is the usual starting point for Edceleste Decider 0.8b: 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.

If memory is tight, the smallest file is Q2_K at 0.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 bymradermacher
FamilyEdceleste
Licenseapache-2.0
Downloads (HF)842
Last updated2026-10-08

Frequently asked questions about Edceleste Decider 0.8b

How much VRAM does Edceleste Decider 0.8b 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 Edceleste Decider 0.8b on an 8 GB GPU?

Yes, with F16: 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 Edceleste Decider 0.8b GGUF?

It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, Q4_K_S is 0.5 GB, IQ4_XS is 0.5 GB and 6 more.

What context length does Edceleste Decider 0.8b 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 Edceleste Decider 0.8b GGUF?

The files are on Hugging Face in the mradermacher/edceleste-decider-0.8b-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 Edceleste Decider 0.8b 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 this model on 8 GB VRAM?

Yes, the Q2_K and Q3_K_S quantizations use about 1.3 GB VRAM at 8 k context, fitting within an 8 GB budget.

Does the model support vision inputs?

No, the model has no vision capability and is trained only on text.

What is the maximum context length?

The model was trained with 262144 tokens, but typical usage is limited to 8 k context for the provided quantizations.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other tiny models

All tiny models →