Luna-f32-GGUF

Luna is a conversational AI model meticulously fine-tuned for immersive roleplay (RP) and dynamic chatting, delivering engaging, character-driven responses that go beyond standard instruction tuning. Designed for creative writing, storytelling, and character interactions, Luna adapts flexibly to a wide range of narrative and roleplay contexts, performing best with well-crafted system prompts that define the character's persona. Whether used as a storytelling companion or for interactive character dialogue, Luna brings a natural, lively conversational style tailored for creative engagement.

Model Files

File Name Quant Type File Size
Luna.BF16.gguf BF16 8.05 GB
Luna.F16.gguf F16 8.05 GB
Luna.F32.gguf F32 16.1 GB
Luna.Q2_K.gguf Q2_K 1.67 GB
Luna.Q3_K_L.gguf Q3_K_L 2.24 GB
Luna.Q3_K_M.gguf Q3_K_M 2.08 GB
Luna.Q3_K_S.gguf Q3_K_S 1.89 GB
Luna.Q4_K_M.gguf Q4_K_M 2.5 GB
Luna.Q4_K_S.gguf Q4_K_S 2.38 GB
Luna.Q5_K_M.gguf Q5_K_M 2.89 GB
Luna.Q5_K_S.gguf Q5_K_S 2.82 GB
Luna.Q6_K.gguf Q6_K 3.31 GB
Luna.Q8_0.gguf Q8_0 4.28 GB

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png

Downloads last month
216
GGUF
Model size
4.02B params
Architecture
qwen3
Hardware compatibility
Log In to view the estimation

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for prithivMLmods/Luna-f32-GGUF

Base model

beyoru/Luna
Quantized
(3)
this model