KO

Kobubu1

KobubuGGUF by KobubuUpdated 2025-11-14
Download on Hugging Face
Parameters30.5B
Context256K
Layers48
Architectureqwen3moe
Smallest quant21.1 GB
Quick answer

Kobubu1 needs about 22.4 GB of memory at Q5_0 (a 21.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Kobubu1 is a 30.5B-parameter Kobubu model in GGUF format, quantized by Kobubu. Its trained context length is 256K tokens. The repository has 1 quant file, from 21.1 GB (Q5_0) to 21.1 GB (Q5_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_021.1 GB 22.4 GB
Too big Get file →

What GPU do you need for Kobubu1?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q5_0 (21.1 GB file, about 22.4 GB in use).

Which Kobubu1 quant should you choose?

Q5_0 (21.1 GB) is the middle option in this repository. 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

Architectureqwen3moe
Parameters30.5B (approximate, mixture of experts)
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized byKobubu
FamilyKobubu
Base modelKobubu/Kobubu1
Downloads (HF)8
Last updated2025-11-14

Frequently asked questions about Kobubu1

How much VRAM does Kobubu1 need?

About 22.4 GB at Q5_0 with an 8K context window. That is the 21.1 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 Kobubu1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kobubu1 GGUF?

It depends on the quant: Q5_0 is 21.1 GB.

What context length does Kobubu1 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Kobubu1 GGUF?

The files are on Hugging Face in the Kobubu/Kobubu1-Q5_0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Kobubu1

Similar models

Browse all →

More from Kobubu

All by Kobubu →

More Kobubu models

All Kobubu →

Other medium models

All medium models →