KA

kanana 1.5 2.1b instruct 2505 grpo cot

KananaGGUF by JJS0321Updated 2025-05-26
Download on Hugging Face
Parameters2.09B
Context32K
Layers32
Architecturellama
Smallest quant4.2 GB
Quick answer

kanana 1.5 2.1b instruct 2505 grpo cot needs about 5.8 GB of memory at F16 (a 4.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

kanana 1.5 2.1b instruct 2505 grpo cot is a 2.09B-parameter Kanana model in GGUF format, quantized by JJS0321. Its trained context length is 32K tokens. The repository has 1 quant file, from 4.2 GB (F16) to 4.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F164.2 GB 5.8 GB
Fits Get file →

What GPU do you need for kanana 1.5 2.1b instruct 2505 grpo cot?

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: the best quant that fits is F16 (4.2 GB file, about 5.8 GB in use).

Which kanana 1.5 2.1b instruct 2505 grpo cot quant should you choose?

F16 (4.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters2.09B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byJJS0321
FamilyKanana
Downloads (HF)15
Last updated2025-05-26

Frequently asked questions about kanana 1.5 2.1b instruct 2505 grpo cot

How much VRAM does kanana 1.5 2.1b instruct 2505 grpo cot need?

About 5.8 GB at F16 with an 8K context window. That is the 4.2 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 kanana 1.5 2.1b instruct 2505 grpo cot on an 8 GB GPU?

Yes, with F16: the 4.2 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of kanana 1.5 2.1b instruct 2505 grpo cot GGUF?

It depends on the quant: F16 is 4.2 GB.

What context length does kanana 1.5 2.1b instruct 2505 grpo cot support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download kanana 1.5 2.1b instruct 2505 grpo cot GGUF?

The files are on Hugging Face in the JJS0321/kanana-1.5-2.1b-instruct-2505-grpo-cot-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from JJS0321

All by JJS0321 →

More Kanana models

All Kanana →

Other tiny models

All tiny models →