KA

kai lite2

KaiGGUF by KOHENOOR-AIUpdated 2026-10-22
Download on Hugging Face
Parameters1.88B
Context256K
Layers24
Architectureqwen35
Smallest quant1.3 GB
Quick answer

kai lite2 needs about 2.2 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. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

kai lite2 is a 1.88B-parameter Kai model in GGUF format, quantized by KOHENOOR-AI. Its trained context length is 256K tokens. The repository has 1 quant file, from 1.3 GB (Q4_K_M) to 1.3 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.3 GB 2.2 GB
Fits Get file →

What GPU do you need for kai lite2?

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 Q4_K_M (1.3 GB file, about 2.2 GB in use).

Which kai lite2 quant should you choose?

Q4_K_M is the usual starting point for kai lite2: it balances file size and quality well. Here it is a 1.3 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters1.88B
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized byKOHENOOR-AI
FamilyKai
Licenseapache-2.0
Downloads (HF)89
Last updated2026-10-22

Frequently asked questions about kai lite2

How much VRAM does kai lite2 need?

About 2.2 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 kai lite2 on an 8 GB GPU?

Yes, with Q4_K_M: the 1.3 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of kai lite2 GGUF?

It depends on the quant: Q4_K_M is 1.3 GB.

What context length does kai lite2 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download kai lite2 GGUF?

The files are on Hugging Face in the KOHENOOR-AI/kai-lite2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does kai lite2 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 KOHENOOR-AI

All by KOHENOOR-AI →

More Kai models

All Kai →

Other tiny models

All tiny models →