KO

Koto Large 106B Preview

KotoGGUF by mradermacherUpdated 2026-10-13
Download on Hugging Face
Parameters106B
Context32K
Layers33
Architecturebailingmoe2
Smallest quant38.9 GB
Quick answer

Koto Large 106B Preview needs about 39.9 GB of memory at Q2_K (a 38.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 38.9 GB (Q2_K) to 46.0 GB (Q3_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 2.2 GB.

Koto Large 106B Preview is a 106B-parameter Koto model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 2 quant files, from 38.9 GB (Q2_K) to 46.0 GB (Q3_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K38.9 GB 39.9 GB
Too big Get file →
Q3_K_S46.0 GB 47.1 GB
Too big Get file →

What GPU do you need for Koto Large 106B Preview?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q3_K_S (46.0 GB file, about 47.1 GB in use).

Which Koto Large 106B Preview quant should you choose?

Q2_K (38.9 GB) is the middle option in this repository. 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

Architecturebailingmoe2
Parameters106B (approximate, mixture of experts)
Layers33
Trained context32,768 tokens
KV cache (fp16)66 KB per token

Source

Quantized bymradermacher
FamilyKoto
Licensemit
Downloads (HF)71
Last updated2026-10-13

Frequently asked questions about Koto Large 106B Preview

How much VRAM does Koto Large 106B Preview need?

About 39.9 GB at Q2_K with an 8K context window. That is the 38.9 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 Koto Large 106B Preview on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 39.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Koto Large 106B Preview GGUF?

It depends on the quant: Q2_K is 38.9 GB, Q3_K_S is 46.0 GB.

What context length does Koto Large 106B Preview support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.2 GB at 32K.

Where can I download Koto Large 106B Preview GGUF?

The files are on Hugging Face in the mradermacher/Koto-Large-106B-Preview-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 Koto Large 106B Preview use?

Hugging Face lists the license as mit. 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 mradermacher

All by mradermacher →

More Koto models

All Koto →

Other large models

All large models →