LU

Luna_12B_V.3

LunaGGUF by mradermacherUpdated 2026-08-13
Download on Hugging Face
Parameters12.8B
Context128K
Layers48
Architecturegemma3
Smallest quant0.0 GB
Quick answer

Luna_12B_V.3 needs about 11.6 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 10.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

12B Gemma3 model focused on roleplaying and everyday assistance

Luna_12B_V.3 is a 12.8B Gemma3 model merged from pre‑trained sources. It excels at roleplaying, context attention, and small detail recall. The model is not overly censored and supports vision, though vision performance is not fully evaluated.

Good at

  • Roleplaying with detailed context
  • Assistant tasks with formatted responses
  • Recall of small details like part numbers or dates

Limits

  • No explicit license information
  • Vision support present but not fully tested
  • No mention of other modalities beyond vision

Best for

  • Creative roleplaying sessions
  • Document‑style assistance tasks
  • Detail‑heavy content generation

Who it’s for. Users who need a 12B model with strong roleplaying and context awareness, especially on RU. It is suitable for developers and content creators looking for a non‑censored assistant with vision capability.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.7 GB
Fits Get file →
IQ1_S3.3 GB 7.0 GB
Fits Get file →
IQ1_M3.5 GB 7.2 GB
Tight Get file →
IQ2_XXS3.9 GB 7.6 GB
Tight Get file →
IQ2_XS4.2 GB 7.9 GB
Tight Get file →
IQ2_S4.5 GB 8.2 GB
Too big Get file →
IQ2_M4.7 GB 8.5 GB
Too big Get file →
Q2_K_S4.8 GB 8.5 GB
Too big Get file →
Q2_K5.1 GB 8.8 GB
Too big Get file →
IQ3_XXS5.2 GB 8.9 GB
Too big Get file →
IQ3_XS5.6 GB 9.4 GB
Too big Get file →
IQ3_S5.9 GB 9.6 GB
Too big Get file →
Q3_K_S5.9 GB 9.6 GB
Too big Get file →
IQ3_M6.1 GB 9.8 GB
Too big Get file →
Q3_K_M6.4 GB 10.2 GB
Too big Get file →
Q3_K_L6.9 GB 10.6 GB
Too big Get file →
IQ4_XS7.1 GB 10.8 GB
Too big Get file →
IQ4_NL7.5 GB 11.2 GB
Too big Get file →
Q4_07.5 GB 11.2 GB
Too big Get file →
Q4_K_S7.5 GB 11.2 GB
Too big Get file →
Q4_K_M7.9 GB 11.6 GB
Too big Get file →
Q4_18.2 GB 11.9 GB
Too big Get file →
Q5_K_S8.9 GB 12.6 GB
Too big Get file →
Q5_K_M9.1 GB 12.9 GB
Too big Get file →
Q6_K10.5 GB 14.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 3.28 GB, memory 7 GB) or IQ1_M (3.49 GB, 7.2 GB). If 12 GB VRAM is available, Q4_K_M (7.87 GB, 11.6 GB) or Q5_K_M (9.14 GB, 12.9 GB) provide higher quality. Smaller quants like IQ2_XXS (3.86 GB, 7.6 GB) are also viable for limited memory.

What GPU do you need for Luna_12B_V.3?

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 the main file (0.0 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.7 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ2_XS (4.2 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (8.2 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (10.5 GB file, about 14.2 GB in use).

Which Luna_12B_V.3 quant should you choose?

Q4_K_M is the usual starting point for Luna_12B_V.3: it balances file size and quality well. Here it is a 7.9 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
Parameters12.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymradermacher
FamilyLuna
Downloads (HF)828
Last updated2026-08-13

Frequently asked questions about Luna_12B_V.3

How much VRAM does Luna_12B_V.3 need?

About 11.6 GB at Q4_K_M with an 8K context window. That is the 7.9 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_12B_V.3 on an 8 GB GPU?

Yes, with IQ2_XS: the 4.2 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Luna_12B_V.3 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.3 GB, IQ1_M is 3.5 GB, IQ2_XXS is 3.9 GB, IQ2_XS is 4.2 GB, IQ2_S is 4.5 GB and 19 more.

What context length does Luna_12B_V.3 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download Luna_12B_V.3 GGUF?

The files are on Hugging Face in the mradermacher/Luna_12B_V.3-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Luna_12B_V.3 on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quant, which use about 7 GB of VRAM at 8k context.

Does the model support vision?

Yes, it is a vision model; mmproj files are available in the static repository.

What is the context length?

The model was trained with 131072 tokens and can handle that context length.

Other GGUFs of Luna_12B_V.3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Luna models

All Luna →

Other medium models

All medium models →