LU

Luna 27B v0

LunaGGUF by mradermacherUpdated 2025-12-11
Download on Hugging Face
Parameters27B
Context128K
Layers62
Architecturegemma3
Smallest quant0.0 GB
Quick answer

Luna 27B v0 needs about 21.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 22.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.

Luna 27B v0 – a Gemma3 finetuned for roleplay and media analysis

Luna 27B v0 is a 27B parameter Gemma3 model fine‑tuned on roleplay data. It shows strong self‑awareness and media analysis capabilities. The model is still a work in progress and may receive further iterations.

Good at

  • Roleplay with consistent persona
  • Media analysis and self‑aware tasks
  • High quality assistant for general queries

Limits

  • No vision support listed
  • Large context requires 131072 tokens
  • License is gemma

Best for

  • Chatbots needing roleplay
  • Content analysis tools
  • Educational assistants

Who it’s for. Developers building conversational agents that require a strong roleplay persona and media analysis. Researchers interested in fine‑tuned Gemma3 models may also find it useful.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 4.7 GB
Fits Get file →
IQ1_S6.3 GB 10.9 GB
Too big Get file →
IQ1_M6.8 GB 11.5 GB
Too big Get file →
IQ2_XXS7.7 GB 12.3 GB
Too big Get file →
IQ2_XS8.4 GB 13.1 GB
Too big Get file →
IQ2_S8.8 GB 13.4 GB
Too big Get file →
IQ2_M9.5 GB 14.2 GB
Too big Get file →
Q2_K_S9.8 GB 14.4 GB
Too big Get file →
Q2_K10.5 GB 15.2 GB
Too big Get file →
IQ3_XXS10.7 GB 15.4 GB
Too big Get file →
IQ3_XS11.6 GB 16.2 GB
Too big Get file →
IQ3_S12.2 GB 16.8 GB
Too big Get file →
Q3_K_S12.2 GB 16.8 GB
Too big Get file →
IQ3_M12.5 GB 17.2 GB
Too big Get file →
Q3_K_M13.4 GB 18.1 GB
Too big Get file →
Q3_K_L14.5 GB 19.2 GB
Too big Get file →
IQ4_XS14.8 GB 19.4 GB
Too big Get file →
Q4_015.6 GB 20.3 GB
Too big Get file →
Q4_K_S15.7 GB 20.3 GB
Too big Get file →
Q4_K_M16.5 GB 21.2 GB
Too big Get file →
Q4_117.2 GB 21.8 GB
Too big Get file →
Q5_K_S18.8 GB 23.4 GB
Too big Get file →
Q5_K_M19.3 GB 23.9 GB
Too big Get file →
Q6_K22.2 GB 26.8 GB
Too big Get file →

For 8 GB VRAM, the Q4_K_M quant (16.55 GB file, 21.2 GB memory at 8k context) is a good balance. If more memory is available, Q5_K_M (19.27 GB file, 23.9 GB memory) offers higher precision. The IQ1_S quant (6.26 GB file, 10.9 GB memory) is suitable for low‑budget setups.

What GPU do you need for Luna 27B v0?

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 the main file (0.0 GB file, about 4.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ1_M (6.8 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (10.7 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.3 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 26.8 GB in use).

Which Luna 27B v0 quant should you choose?

Q4_K_M is the usual starting point for Luna 27B v0: it balances file size and quality well. Here it is a 16.5 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters27B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized bymradermacher
FamilyLuna
Licensegemma
Downloads (HF)361
Last updated2025-12-11

Frequently asked questions about Luna 27B v0

How much VRAM does Luna 27B v0 need?

About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Luna 27B v0 on an 8 GB GPU?

Yes, with the smaller files: the 0.0 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 Luna 27B v0 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 6.3 GB, IQ1_M is 6.8 GB, IQ2_XXS is 7.7 GB, IQ2_XS is 8.4 GB, IQ2_S is 8.8 GB and 18 more.

What context length does Luna 27B v0 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.

Where can I download Luna 27B v0 GGUF?

The files are on Hugging Face in the mradermacher/Luna-27B-v0-i1-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 Luna 27B v0 use?

Hugging Face lists the license as gemma. 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 Luna 27B v0 on 8 GB VRAM?

The Q4_K_M quant requires about 21.2 GB memory at 8k context, so 8 GB VRAM is insufficient. Use a smaller quant such as IQ1_S if memory is limited.

Does Luna 27B v0 support vision tasks?

No vision support is listed; the model is text‑only.

What is the recommended system prompt?

Use "You are Luna, a helpful and harmless language model by Allura." to elicit full capabilities.

Other GGUFs of Luna-27B-v0

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Luna models

All Luna →

Other medium models

All medium models →