LU

Luna v2 9B Merged

LunaGGUF by mradermacherUpdated 2026-10-07
Download on Hugging Face
Parameters9.2B
Context256K
Layers33
Architectureqwen35
Smallest quant3.9 GB
Quick answer

Luna v2 9B Merged needs about 7.4 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 3.9 GB (Q2_K) to 18.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Luna v2 9B Merged – 9.2B Qwen3.5 conversational model

Luna v2 9B Merged is a 9.2B parameter Qwen3.5 model with merged LoRA weights. It supports reasoning and tool use. The model is released under Apache‑2.0 and trained on a 262144 token context.

Good at

  • Conversational reasoning
  • Tool invocation
  • Informal slang

Limits

  • No vision support
  • Requires 8k context for estimates
  • Large VRAM for higher quants

Best for

  • Chatbot development
  • Tool‑enabled assistants
  • Testing conversational AI

Who it’s for. Developers building conversational agents who need a lightweight, open‑source model with reasoning and tool‑use capabilities. The model is suitable for projects that can accommodate its 8k context size and 9.2B parameter count.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.9 GB 5.5 GB
Fits Get file →
Q3_K_S4.4 GB 6.0 GB
Fits Get file →
Q3_K_M4.7 GB 6.3 GB
Fits Get file →
Q3_K_L5.0 GB 6.7 GB
Fits Get file →
IQ4_XS5.4 GB 7.0 GB
Fits Get file →
Q4_K_S5.5 GB 7.1 GB
Fits Get file →
Q4_K_M5.8 GB 7.4 GB
Tight Get file →
Q5_K_S6.5 GB 8.1 GB
Too big Get file →
Q5_K_M6.6 GB 8.2 GB
Too big Get file →
Q6_K7.6 GB 9.2 GB
Too big Get file →
Q8_09.8 GB 11.4 GB
Too big Get file →
F1618.4 GB 20.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 5.78 GB, estimated memory 7.4 GB). For 4 GB VRAM, use Q2_K (file size 3.91 GB, estimated memory 5.5 GB). For higher quality with 12 GB VRAM, Q5_K_M (file size 6.64 GB, estimated memory 8.2 GB) is recommended.

What GPU do you need for Luna v2 9B Merged?

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 Q3_K_S (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (5.8 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 11.4 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (18.4 GB file, about 20.0 GB in use).

Which Luna v2 9B Merged quant should you choose?

Q4_K_M is the usual starting point for Luna v2 9B Merged: it balances file size and quality well. Here it is a 5.8 GB file.

The Q8_0 file is 9.8 GB, about 1.7 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 3.9 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
Parameters9.2B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized bymradermacher
FamilyLuna
Licenseapache-2.0
Downloads (HF)918
Last updated2026-10-07

Frequently asked questions about Luna v2 9B Merged

How much VRAM does Luna v2 9B Merged need?

About 7.4 GB at Q4_K_M with an 8K context window. That is the 5.8 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 v2 9B Merged on an 8 GB GPU?

Yes, with Q4_K_M: the 5.8 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Luna v2 9B Merged GGUF?

It depends on the quant: Q2_K is 3.9 GB, Q3_K_S is 4.4 GB, Q3_K_M is 4.7 GB, Q3_K_L is 5.0 GB, IQ4_XS is 5.4 GB, Q4_K_S is 5.5 GB and 6 more.

What context length does Luna v2 9B Merged support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download Luna v2 9B Merged GGUF?

The files are on Hugging Face in the mradermacher/Luna-v2-9B-Merged-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 v2 9B Merged 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 Luna v2 9B Merged on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 7.4 GB of VRAM at 8k context, fitting within an 8 GB GPU.

Does this model support vision tasks?

No, the model has no vision capability and is purely text‑based.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Luna-v2-9B-Merged

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Luna models

All Luna →

Other small models

All small models →