Kanana Nano 2.1b Instruct Ko Reasoning 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 25 quants, from 0.0 GB to 2.0 GB (Q6_K).
Kanana Nano 2.1b Instruct Ko Reasoning – Korean logical reasoning model
Kanana Nano 2.1b Instruct Ko Reasoning is a fine‑tuned Korean reasoning model based on kakaocorp/kanana-nano-2.1b-instruct. It is optimized for logical and multi‑hop reasoning tasks in Korean. The model was released in Mar 2025 and is available in multiple GGUF quantizations.
Good at
- Logical reasoning in Korean
- Multi‑hop question answering
- Tool‑use instruction following
Limits
- No vision support
- License cc‑by‑nc‑4.0
- Context length 8192 tokens
Best for
- Korean academic tutoring
- Korean legal document analysis
- Korean chatbot reasoning tasks
Who it’s for. Researchers and developers needing a Korean‑specific reasoning LLM. The model is open‑source but non‑commercial use only due to its license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ1_S | 0.8 GB | 2.4 GB | Fits | Get file → | |
| IQ1_M | 0.8 GB | 2.4 GB | Fits | Get file → | |
| IQ2_XXS | 0.9 GB | 2.4 GB | Fits | Get file → | |
| IQ2_XS | 0.9 GB | 2.5 GB | Fits | Get file → | |
| IQ2_S | 1.0 GB | 2.5 GB | Fits | Get file → | |
| Q2_K_S | 1.0 GB | 2.6 GB | Fits | Get file → | |
| IQ2_M | 1.0 GB | 2.6 GB | Fits | Get file → | |
| Q2_K | 1.0 GB | 2.6 GB | Fits | Get file → | |
| IQ3_XXS | 1.1 GB | 2.6 GB | Fits | Get file → | |
| IQ3_XS | 1.1 GB | 2.7 GB | Fits | Get file → | |
| IQ3_S | 1.2 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_S | 1.2 GB | 2.7 GB | Fits | Get file → | |
| IQ3_M | 1.2 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_M | 1.2 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_L | 1.3 GB | 2.9 GB | Fits | Get file → | |
| IQ4_XS | 1.3 GB | 2.9 GB | Fits | Get file → | |
| IQ4_NL | 1.4 GB | 2.9 GB | Fits | Get file → | |
| Q4_0 | 1.4 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_S | 1.4 GB | 3.0 GB | Fits | Get file → | |
| Q4_1 | 1.5 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_M | 1.5 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_S | 1.7 GB | 3.2 GB | Fits | Get file → | |
| Q5_K_M | 1.7 GB | 3.3 GB | Fits | Get file → | |
| Q6_K | 2.0 GB | 3.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.52 GB file, ~3.1 GB memory). For 12 GB VRAM, Q5_K_M (1.74 GB file, ~3.3 GB memory). For 16 GB VRAM, Q6_K (2.02 GB file, ~3.6 GB memory). Memory estimates are approximate.
What GPU do you need for Kanana Nano 2.1b Instruct Ko Reasoning?
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 Q6_K (2.0 GB file, about 3.6 GB in use).
Which Kanana Nano 2.1b Instruct Ko Reasoning quant should you choose?
Q4_K_M is the usual starting point for Kanana Nano 2.1b Instruct Ko Reasoning: it balances file size and quality well. Here it is a 1.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Kanana Nano 2.1b Instruct Ko Reasoning
How much VRAM does Kanana Nano 2.1b Instruct Ko Reasoning 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 Kanana Nano 2.1b Instruct Ko Reasoning on an 8 GB GPU?
Yes, with Q6_K: the 2.0 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Kanana Nano 2.1b Instruct Ko Reasoning GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.8 GB, IQ1_M is 0.8 GB, IQ2_XXS is 0.9 GB, IQ2_XS is 0.9 GB, IQ2_S is 1.0 GB and 19 more.
What context length does Kanana Nano 2.1b Instruct Ko Reasoning support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.
Where can I download Kanana Nano 2.1b Instruct Ko Reasoning GGUF?
The files are on Hugging Face in the mradermacher/kanana-nano-2.1b-instruct-Ko-Reasoning-i1-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 Kanana Nano 2.1b Instruct Ko Reasoning use?
Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 3.1 GB of VRAM at 8 k context, which fits within 8 GB.
Does this model support vision tasks?
No, the model has no vision capability.
Is the model free for commercial use?
No, the cc‑by‑nc‑4.0 license allows non‑commercial use only.