KU

KULLM3

KullmGGUF by mskim92Updated 2024-10-02
Download on Hugging Face
Parameters10.7B
Context4K
Layers48
Architecturellama
Smallest quant6.5 GB
Quick answer

KULLM3 needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU.

KULLM3 is a 10.7B-parameter Kullm model in GGUF format, quantized by mskim92. Its trained context length is 4K tokens. The repository has 1 quant file, from 6.5 GB (Q4_K_M) to 6.5 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M6.5 GB 7.8 GB
Tight Get file →

What GPU do you need for KULLM3?

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: the best quant that fits is Q4_K_M (6.5 GB file, about 8.6 GB in use).

Which KULLM3 quant should you choose?

Q4_K_M is the usual starting point for KULLM3: it balances file size and quality well. Here it is a 6.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.7B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymskim92
FamilyKullm
Licenseapache-2.0
Downloads (HF)8
Last updated2024-10-02

Frequently asked questions about KULLM3

How much VRAM does KULLM3 need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 KULLM3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of KULLM3 GGUF?

It depends on the quant: Q4_K_M is 6.5 GB.

What context length does KULLM3 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download KULLM3 GGUF?

The files are on Hugging Face in the mskim92/KULLM3-Q4_K_M-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 KULLM3 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.

Other GGUFs of KULLM3

Similar models

Browse all →

More Kullm models

All Kullm →

Other medium models

All medium models →