KA

Kanso Koi 1.0 M2 original-base F16 control

KansoGGUF by BuilderHelmUpdated 2026-11-03
Download on Hugging Face
Parameters2.03B
Context40K
Layers28
Architectureqwen3
Smallest quant1.3 GB
Quick answer

Kanso Koi 1.0 M2 original-base F16 control needs about 2.7 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.3 GB (Q4_K_M) to 4.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Kanso Koi 1.0 M2 original-base F16 control is a 2.03B-parameter Kanso model in GGUF format, quantized by BuilderHelm. Its trained context length is 40K tokens. The repository has 5 quant files, from 1.3 GB (Q4_K_M) to 4.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.3 GB 2.7 GB
Fits Get file →
Q5_K_M1.5 GB 2.9 GB
Fits Get file →
Q6_K1.7 GB 3.1 GB
Fits Get file →
Q8_02.2 GB 3.6 GB
Fits Get file →
F164.1 GB 5.5 GB
Fits Get file →

What GPU do you need for Kanso Koi 1.0 M2 original-base F16 control?

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: the best quant that fits is Q8_0 (2.2 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (4.1 GB file, about 5.5 GB in use).

Which Kanso Koi 1.0 M2 original-base F16 control quant should you choose?

Q4_K_M is the usual starting point for Kanso Koi 1.0 M2 original-base F16 control: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 2.2 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters2.03B
Layers28
Trained context40,960 tokens
KV cache (fp16)112 KB per token

Source

Quantized byBuilderHelm
FamilyKanso
Licenseapache-2.0
Downloads (HF)353
Last updated2026-11-03

Frequently asked questions about Kanso Koi 1.0 M2 original-base F16 control

How much VRAM does Kanso Koi 1.0 M2 original-base F16 control need?

About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Kanso Koi 1.0 M2 original-base F16 control on an 8 GB GPU?

Yes, with F16: the 4.1 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kanso Koi 1.0 M2 original-base F16 control GGUF?

It depends on the quant: Q4_K_M is 1.3 GB, Q5_K_M is 1.5 GB, Q6_K is 1.7 GB, Q8_0 is 2.2 GB, F16 is 4.1 GB.

What context length does Kanso Koi 1.0 M2 original-base F16 control support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Kanso Koi 1.0 M2 original-base F16 control GGUF?

The files are on Hugging Face in the BuilderHelm/Kanso-Koi-1.0-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 Kanso Koi 1.0 M2 original-base F16 control 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.

Similar models

Browse all →

More from BuilderHelm

All by BuilderHelm →

Other tiny models

All tiny models →