LocalClaw/LLM/Raon-1 mini preview
Open-weight MoE

Raon-1 mini preview

Use case: Coding assistant. Check the memory fit and choose a setup path below.

32 GB short-context planning estimate32 GB RAMQ4_K_MCoding assistant
Choose an app

This model needs a special runtime. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
UnslothNot available for this model
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloads
llama.cppNot available for this model
Use with LocalClawOptional workspace after the model is installed
This model needs its official runtimeKRAFTON llama.cpp branch raon-1-mini-preview; upstream support pending
Parameters
28.8B (4.3B active, MoE)
RAM planning estimate
32 GB
Model size
19.69 GB
Quantization
Q4_K_M

About Raon-1 mini preview

Catalogue summary: KRAFTON Apache 2.0 model trained from scratch, focused on Korean conversation and agentic tasks. Official Q4_K_M GGUF is 19.69GB. Plan for 32GB RAM at short context. Preview release requires the KRAFTON llama.cpp branch; 262K context needs separate memory planning.

Raon-1 mini preview has a 32 GB short-context RAM planning estimate based on its 19.69 GB GGUF. This is not a measured minimum or a guarantee at maximum context.

Use the official KRAFTON llama.cpp branch raon-1-mini-preview; upstream support pending setup. The current low-bit files are not a stock LM Studio install.

Model sourcePublic GGUF repository (verified 2026-11-06): KRAFTON/Raon-1-mini-preview-ggufUpstream releaseLicence text
chatcodereasoningtool-callingmultilingual

Install path

01
Check RAM fitPlan for 32 GB RAM at short context; this is an estimate. Use Q4_K_M.
02
Load the modelFollow the official KRAFTON llama.cpp branch raon-1-mini-preview; upstream support pending instructions. Stock LM Studio support is not confirmed.
03
Try your workloadStart with a short prompt, check memory use and adjust context length before running longer tasks.

Download formats for this model

These are quantizations of the same model. The RAM fit above uses Q4_K_M; larger files need more memory. File sizes exclude the runtime, context cache and optional vision projector.

Catalogue record

  • Family: raon
  • Parameters: 28.8B (4.3B active, MoE)
  • Recommended quantization: Q4_K_M
  • Short-context RAM estimate: 32 GB
  • Catalogue model size: 19.69 GB
  • Tags: chat, code, reasoning, tool-calling, multilingual

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Reading the scores

LocalClaw /10 is an editorial catalogue rating. Community /5 comes from member reviews. Your machine fit is a separate memory and runtime assessment.

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
?
quality
?
coding
?
reasoning
?

Technical notes

Developer
KRAFTON AI
License
Apache 2.0
Context window
262,144 tokens
Architecture
28.8B MoE with 4.3B active parameters, 18 Raon Delta Attention layers, 7 full-attention layers and Raon-mHC residual connections.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Comfortable headroomMac mini M4 Pro 48GBMobile workstationMacBook Pro M4 Max 36GBPower-user picks32GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Agents-A1 35B (3B active, MoE)Granite 4.2 (30B) 29.3BNex-N2.5-mini 35B MoEOccamy-1.0 35B (3B active, MoE)Ornith 1.0 35B GGUF 35B MoESarvam 30B 32B (2.4B active, MoE)Xing4.0-29B-A4B 29B (4B active, MoE)LFM2.5-24B-A2B 24B (2.45B active, MoE)

Where to go next