KA

kakaocorp/kanana-1.5-2.1b-instruct-2505

KakaocorpGGUF by bibekyessUpdated 2025-09-11
Download on Hugging Face
Parameters2.32B
Context32K
Layers32
Architecturellama
Smallest quant1.5 GB
Quick answer

kakaocorp/kanana-1.5-2.1b-instruct-2505 needs about 3.1 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.5 GB (Q4_K_M) to 4.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

kakaocorp/kanana-1.5-2.1b-instruct-2505 is a 2.32B-parameter Kakaocorp model in GGUF format, quantized by bibekyess. Its trained context length is 32K tokens. The repository has 2 quant files, from 1.5 GB (Q4_K_M) to 4.6 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.5 GB 3.1 GB
Fits Get file →
—4.6 GB 6.2 GB
Fits Get file →

What GPU do you need for kakaocorp/kanana-1.5-2.1b-instruct-2505?

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 (1.5 GB file, about 3.1 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (1.5 GB file, about 3.1 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (4.6 GB file, about 6.2 GB in use).

Which kakaocorp/kanana-1.5-2.1b-instruct-2505 quant should you choose?

Q4_K_M is the usual starting point for kakaocorp/kanana-1.5-2.1b-instruct-2505: it balances file size and quality well. Here it is a 1.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters2.32B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybibekyess
FamilyKakaocorp
Licenseapache-2.0
Downloads (HF)10
Last updated2025-09-11

Frequently asked questions about kakaocorp/kanana-1.5-2.1b-instruct-2505

How much VRAM does kakaocorp/kanana-1.5-2.1b-instruct-2505 need?

About 3.1 GB at Q4_K_M with an 8K context window. That is the 1.5 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 kakaocorp/kanana-1.5-2.1b-instruct-2505 on an 8 GB GPU?

Yes, with the smaller files: the 4.6 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of kakaocorp/kanana-1.5-2.1b-instruct-2505 GGUF?

It depends on the quant: Q4_K_M is 1.5 GB, file is 4.6 GB.

What context length does kakaocorp/kanana-1.5-2.1b-instruct-2505 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 kakaocorp/kanana-1.5-2.1b-instruct-2505 GGUF?

The files are on Hugging Face in the bibekyess/kanana-1.5-2.1b-instruct-2505-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 kakaocorp/kanana-1.5-2.1b-instruct-2505 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 Kakaocorp models

All Kakaocorp →

Other tiny models

All tiny models →