selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

KRAFTON logo

Raon-1-nano

KRAFTON·Instruct·released 29 Oct 2026

Apache 2.03.5B256K ctx ≈5.6 GB
Your GPU
ollama run hf.co/KRAFTON/Raon-1-nano-gguf:Q4_K_M
All 5 runners ↓

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.

Notify me when

How much VRAM does Raon-1-nano need?

At Q4_K_M Raon-1-nano needs about 5.6 GB with an 8K context (5.6 GB at Q4, 10 GB at full precision). Pick your GPU to see what fits and how fast it runs.

--vram
any
--gpus
--quant

Needs: ≈5.5 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.

Change quant, context or KV cache to compare
Advanced: context 8K · KV cache 16-bit
Context
KV cache

Smallest GPU for each quant and context (KV cache 16-bit)

Quantisation8K16K32K64K128K256K
Q3_K_M
Q4_K_M
Q5_K_M
Q6_K
Q8_0
FP16

≤16 GB card24–32 GB48–96 GBmore

QuantisationQualityWeightsKV cacheTotal
Q2_KHeavy lossSmallest, noticeably worse qualityHeavy loss1.1 GB est.3.0 GB≈4.6 GB
Q3_K_MNoticeable lossSmall, some quality lossNoticeable loss1.6 GB est.3.0 GB≈5.2 GB
Q4_K_MrecommendedSmall lossRecommended default for local useSmall loss1.9 GB file3.0 GB≈5.5 GB
Q5_K_MNear-losslessNear-lossless for most tasksNear-lossless2.4 GB file3.0 GB≈6.0 GB
Q6_KNear-losslessPractically losslessNear-lossless2.5 GB file3.0 GB≈6.1 GB
Q8_0LosslessLossless in practice, twice the size of Q4Lossless3.2 GB file3.0 GB≈6.8 GB
FP16 / BF16LosslessFull precision, as releasedLossless5.8 GB file3.0 GB≈9.6 GB

Estimates for 8K tokens of context: weights + KV cache + runtime overhead. Speed assumes memory-bound decoding at your GPU’s bandwidth. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.

How to pick a quant

Take the biggest quant that fits with room left for context. Q4_K_M is the usual sweet spot. Below Q4 quality drops fast, above Q6 you mostly pay memory for nothing. Big models (70B+, large MoE) tolerate low quants better than small ones.

  • LosslessF16, Q8_0
  • Near-losslessQ6_K, Q5_K_M
  • Small lossQ5_K_S, Q4_K_M, IQ4_NL, IQ4_XS, Q4_K_S
  • Noticeable lossQ4_0, Q3_K_L, Q3_K_M, IQ3_M
  • Heavy lossIQ3_XXS, Q3_K_S, IQ2_M, Q2_K

Typical quality loss, not measured per model. Tiers come from KL divergence against FP16 on Llama 3 8B: llama.cpp perplexity README: LLaMA 3 8B scoreboard (KLD and ΔPPL vs FP16, Wikitext-2); llama.cpp quantize tool: ΔPPL per quant type @ Llama-3-8B

How much context fits?

Model quant
KV cache

At 8K context, Q4_K_M needs ≈5.5 GB(1.9 GB weights + 3.0 GB KV cache + 0.6 GB overhead). Pick a GPU above to see how much context fits.

0501001K2K4K8K16K32K64K128K256KGB

Weights + overheadKV cache

Can the RTX 4060 run Raon-1-nano? →

Speed vs quality per quant

Smaller quants run faster and fit in less memory, but lose quality.

Q2_KQ3_K_MQ4_K_MQ5_K_MQ6_KQ8_0F16

Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.

Real-world speed of Raon-1-nano

Tokens per second measured by people running it at home. A GPU shows a median once 3 reports agree on the same setup. Reports far from our estimate wait for a review. Measure yours with llama-bench →

No medians yet. Be one of the first 3 to report a setup.

All reports

Run Raon-1-nano locally

--quantQ4_K_Mdefault; pick your GPU to tailor itKRAFTON/Raon-1-nano-gguf

Q4_K_M straight from Hugging Facedocs
ollama run hf.co/KRAFTON/Raon-1-nano-gguf:Q4_K_M

Install Ollama

OpenAI-compatible server with a web UIdocs
llama-server -hf KRAFTON/Raon-1-nano-gguf:Q4_K_M

Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.

Install llama.cpp

Download with the lms CLIdocs
lms get KRAFTON/Raon-1-nano-gguf@Q4_K_M

Then load it from the LM Studio app or with `lms load`.

Install LM Studio

Apple Silicon with mlx-lmdocs
bash
pip install mlx-lm
mlx_lm.generate --model KRAFTON/Raon-1-nano-mlx --prompt "Hello"

Use `mlx_lm.chat` with the same --model for an interactive chat.

OpenAI-compatible serverdocs
mlx_lm.server --model KRAFTON/Raon-1-nano-mlx --port 8080

API on http://localhost:8080/v1.

Install MLX

Chat with the pipeline APIdocs
python
from transformers import pipeline

pipe = pipeline("text-generation", model="KRAFTON/Raon-1-nano", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])

Install Transformers

Quantised versions and downloads

RepositoryFormatQuantSizeDownloads
KRAFTON/Raon-1-nano-ggufGGUFQ4_K_M2.1 GB148
webmp3/Sakura-Raon-1-nano-GGUFGGUFQ4_K_M2.1 GB—
webmp3/Sakura-Raon-1-nano-GGUFGGUFQ5_K_M2.6 GB—
KRAFTON/Raon-1-nano-ggufGGUFQ6_K2.6 GB148
webmp3/Sakura-Raon-1-nano-GGUFGGUFQ6_K2.6 GB—
KRAFTON/Raon-1-nano-ggufGGUFQ6_K_MTP2.7 GB148
KRAFTON/Raon-1-nano-ggufGGUFQ8_03.4 GB148
webmp3/Sakura-Raon-1-nano-GGUFGGUFQ8_03.4 GB—
KRAFTON/Raon-1-nano-ggufGGUFQ8_0_MTP3.5 GB148
KRAFTON/Raon-1-nano-ggufGGUFF166.3 GB148

About 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. 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.

Full model card on Hugging Face →

Alternatives to Raon-1-nano

All alternatives →
nvidia logo≈4.2 GB

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.

4B256K ctx nvidia-nemotron-open-model-license
1.9MMar 2026gguf
ibm-granite logo

granite-4.1-3b

ibm-granite·Chat

≈3.1 GB

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.

3.4B128K ctx Apache 2.0
456.9KApr 2026ollama
openbmb logo

MiniCPM5-2B

openbmb·Chat

≈2.3 GB

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.

2.5B128K ctx Apache 2.0
1MSept 2026gguf
Qwen logo≈4.0 GB

We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements:

4B256K ctx Apache 2.0
2.6MAug 2025gguf
ibm-granite logo

granite-4.2-3b

ibm-granite·Chat

≈3.3 GB

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.

3.7B128K ctx Apache 2.0
42.4KAug 2026ollama
Qwen logo

Qwen3-4B

Qwen·Chat

≈4.0 GB

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

4B40K ctx Apache 2.0
3.2MApr 2025ollama

Raon-1-nano 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.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.