GL

Merge B

GlitterfettiGGUF by ArtusDevUpdated 2025-03-26
Download on Hugging Face
Parameters11.8B
Context128K
Layers48
Architecturegemma3
Smallest quant8.4 GB
Quick answer

Merge B needs about 13.4 GB of memory at Q6_K (a 9.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 8.4 GB (Q5_K_M) to 12.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Merge B is a 11.8B-parameter Glitterfetti model in GGUF format, quantized by ArtusDev. Its trained context length is 128K tokens. The repository has 3 quant files, from 8.4 GB (Q5_K_M) to 12.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M8.4 GB 12.2 GB
Too big Get file →
Q6_K9.7 GB 13.4 GB
Too big Get file →
Q8_012.5 GB 16.2 GB
Too big Get file →

What GPU do you need for Merge B?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q6_K (9.7 GB file, about 13.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (12.5 GB file, about 16.2 GB in use).

Which Merge B quant should you choose?

Q6_K (9.7 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q5_K_M at 8.4 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters11.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized byArtusDev
Licensegemma
Downloads (HF)21
Last updated2025-03-26

Frequently asked questions about Merge B

How much VRAM does Merge B need?

About 13.4 GB at Q6_K with an 8K context window. That is the 9.7 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 Merge B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Merge B GGUF?

It depends on the quant: Q5_K_M is 8.4 GB, Q6_K is 9.7 GB, Q8_0 is 12.5 GB.

What context length does Merge B 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 Merge B GGUF?

The files are on Hugging Face in the ArtusDev/ToastyPigeon_glitterfetti-merge-B-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 Merge B 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.

Similar models

Browse all →

More from ArtusDev

All by ArtusDev →

More Glitterfetti models

All Glitterfetti →

Other medium models

All medium models →