# Raon-1-nano

> Raon-1 nano is a dense language model with 1.5B effective parameters (3.1B total, including a 1.5B per-layer embedding table), developed by KRAFTON AI. It is designed to follow instructions, maintain conversational context, and call the right tools in both Korean and English.

- **Organisation:** KRAFTON
- **Category:** Chat & Text Generation
- **Parameters:** 3.5B
- **Context length:** 262,144 tokens
- **Licence:** Apache 2.0 (Commercial use OK)
- **Released:** 2026-10-29
- **Hugging Face:** 1.3K downloads (30 days), 95 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 4.63 |
| Q3_K_M | 5.19 |
| Q4_K_M | 5.59 |
| Q5_K_M | 5.96 |
| Q6_K | 6.34 |
| Q8_0 | 7.17 |
| F16 | 10.4 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [LM Studio](https://lmstudio.ai)
- [MLX](https://github.com/ml-explore/mlx-lm)
- [Transformers](https://github.com/huggingface/transformers)
- [Jan](https://jan.ai) (community)
- [KoboldCpp](https://selfhost.directory/project/koboldcpp) (community)
- [LocalAI](https://selfhost.directory/project/localai) (community)
- [Ollama](https://selfhost.directory/project/ollama) (community)

## About

Raon-1 nano is a dense language model with 1.5B effective parameters (3.1B total, including a 1.5B per-layer embedding table), developed by KRAFTON AI. It is designed to follow instructions, maintain conversational context, and call the right tools in both Korean and English. As part of the Raon open model family, it is released under the Apache 2.0 license.

• Faithful, natural conversation: Leads the comparison models on the instruction-following, context-following, and Korean conversation benchmarks shown below.
• Korean and English: Trained on Korean and English, with solid English capabilities alongside its Korean strengths.
• Tool calling: Tool calling within conversations, for everyday tasks such as office work and mobile control.
• On-device deployment: Available in GGUF, MLX, and LiteRT-LM formats for local inference, including on Apple silicon.
• Long context: Natively supports up to 262,144 tokens of context.

Raon-1 nano uses a hybrid dense architecture, consisting of 18 linear attention layers and 6 full attention layers.

## Alternatives

- [nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16](https://selfhost.directory/models/nvidia/nvidia-nemotron-3-nano-4b-bf16) (4B, nvidia-nemotron-open-model-license, ≈4.17 GB at Q4): NVIDIA-Nemotron-3-Nano-4B-BF16 is a small language model (SLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response.
- [ibm-granite/granite-4.1-3b](https://selfhost.directory/models/ibm-granite/granite-4.1-3b) (3.4B, Apache 2.0, ≈3.14 GB at Q4): Model Summary: Granite-4.1-3B is a 3B parameter long-context instruct model finetuned from Granite-4.1-3B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.
- [openbmb/MiniCPM5-2B](https://selfhost.directory/models/openbmb/minicpm5-2b) (2.5B, Apache 2.0, ≈2.32 GB at Q4): We are releasing MiniCPM5-2B, the second model in the MiniCPM5 series, following MiniCPM5-1B. It is a dense 2B Transformer that scales up the same training recipe, built for on-device, local deployment, and resource-constrained scenarios, reaching 2B-class open-source SOTA.
- [Qwen/Qwen3-4B-Instruct-2507](https://selfhost.directory/models/qwen/qwen3-4b-instruct-2507) (4B, Apache 2.0, ≈4.01 GB at Q4): We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements:
- [ibm-granite/granite-4.2-3b](https://selfhost.directory/models/ibm-granite/granite-4.2-3b) (3.7B, Apache 2.0, ≈3.29 GB at Q4): Granite is a family of open-source large language models developed by IBM, designed for enterprise and research use. Granite models are built to be versatile, safe, and efficient — covering a range of sizes and capabilities from compact edge-deployable models to large-scale reasoning systems.
- [Qwen/Qwen3-4B](https://selfhost.directory/models/qwen/qwen3-4b) (4B, Apache 2.0, ≈4.01 GB at Q4): Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

More: https://selfhost.directory/models/krafton/raon-1-nano/alternatives

## Runs well on

- [GeForce RTX 4060](https://selfhost.directory/models/krafton/raon-1-nano/on/rtx-4060): Q8_0, est. 40 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/krafton/raon-1-nano/on/apple-m4-16gb): F16, est. 9.3 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/krafton/raon-1-nano/on/rx-6700-xt): F16, est. 30 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/krafton/raon-1-nano/on/rtx-3060): F16, est. 28 tok/s
- [Arc B580](https://selfhost.directory/models/krafton/raon-1-nano/on/arc-b580): F16, est. 36 tok/s
- [Tesla T4](https://selfhost.directory/models/krafton/raon-1-nano/on/tesla-t4): F16, est. 25 tok/s

## Similar size

- [meta-llama/Llama-3.2-3B-Instruct](https://selfhost.directory/models/meta-llama/llama-3.2-3b-instruct) (3.2B)
- [Qwen/Qwen3-4B](https://selfhost.directory/models/qwen/qwen3-4b) (4B)
- [Qwen/Qwen2.5-3B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-3b-instruct) (3.1B)
- [openbmb/MiniCPM5-2B](https://selfhost.directory/models/openbmb/minicpm5-2b) (2.5B)
- [microsoft/Phi-4-mini-instruct](https://selfhost.directory/models/microsoft/phi-4-mini-instruct) (3.8B)
- [google/gemma-2-2b-it](https://selfhost.directory/models/google/gemma-2-2b-it) (2.6B)

## FAQ

**How much VRAM does Raon-1-nano need?**
About 5.6 GB at Q4_K_M with an 8K context. Q8_0 needs about 7.2 GB and full precision about 10 GB. Longer contexts need more memory for the KV cache.

**Can Raon-1-nano run on the RTX 4060?**
Yes. It fits at Q8_0 (about 6.8 GB), at an estimated 40 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.

**Can I use Raon-1-nano commercially?**
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.

**What is the context length of Raon-1-nano?**
262,144 tokens (256K). The full window needs far more memory than an 8K context.

**How do I run Raon-1-nano with Ollama or llama.cpp?**
With Ollama: ollama run hf.co/KRAFTON/Raon-1-nano-gguf:Q4_K_M. With llama.cpp: llama-server -hf KRAFTON/Raon-1-nano-gguf:Q4_K_M, which starts an OpenAI-compatible server.

## Links

- huggingface: https://huggingface.co/KRAFTON/Raon-1-nano
- github: https://github.com/krafton-ai/vllm
- paper: https://arxiv.org/abs/2605.28207

---
Source: https://selfhost.directory/models/krafton/raon-1-nano