Raon-1 mini Preview (30B-A4B) on NVIDIA H800 80GB SXM

Can the NVIDIA H800 80GB SXM run Raon-1 mini Preview (30B-A4B)?

Yes, it runs great

Runs great. At F16 it needs about 62.2 GB of 80.0 GB usable, with an estimated speed of 113 tok/s.

Best quant: F16
Generation speed: 113 tok/s
Prompt processing: 22,404 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

Best app to run it on the NVIDIA H800 80GB SXM

On Linux

vLLM

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

vllm serve KRAFTON/Raon-1-mini-preview

SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
Docker Model Runner Handy if you already work in Docker.

On Windows

vLLM

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
On Windows it runs through WSL2.

vllm serve KRAFTON/Raon-1-mini-preview

SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
Docker Model Runner Handy if you already work in Docker.

Want an agent? Raon-1 mini Preview (30B-A4B) supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Raon-1 mini Preview (30B-A4B)

Original weights · Hugging Face

Full-precision files from KRAFTON, for fine-tuning, vLLM, Transformers.

huggingface.co/KRAFTON/Raon-1-mini-preview (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from KRAFTON. The weights themselves download from Hugging Face.

github.com/krafton-ai/Raon-1-mini-preview (opens in a new tab)

KRAFTON's official repo. KRAFTON also publishes GGUF files (KRAFTON/Raon-1-mini-preview-gguf), but for now they need KRAFTON's llama.cpp fork (krafton-ai/llama.cpp) because upstream llama.cpp support is still pending, so LM Studio and Ollama cannot load them yet. An official MLX version is at KRAFTON/Raon-1-mini-preview-mlx.

git clone https://github.com/krafton-ai/Raon-1-mini-preview

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 88Excellent quality (A+) · 88 of 100: how capable the model is at F16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at F16, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the NVIDIA H800 80GB SXM: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	39.6 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	94.6 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA H800 80GB SXM

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	16.2 GB	80.0 GB	266 tok/s	Runs great	61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q3_K_M`	18.8 GB	80.0 GB	247 tok/s	Runs great	73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q4_K_M`	22.2 GB	80.0 GB	227 tok/s	Runs great	83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	25.1 GB	80.0 GB	210 tok/s	Runs great	85Excellent quality (A+) · 85 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	28.3 GB	80.0 GB	195 tok/s	Runs great	87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	35.2 GB	80.0 GB	171 tok/s	Runs great	88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	62.2 GB	80.0 GB	113 tok/s	Runs great	88Excellent quality (A+) · 88 of 100: how capable the model is at F16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) Q8_0 · 42.0 tok/s · Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q8_0 · 54.2 tok/s · Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at F16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell F16 · 78.7 tok/s · Runs great
87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 156 tok/s · Runs great
87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (48 GB) Q6_K · 39.9 tok/s · Runs great
83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 132 tok/s · Runs great

Quick answers

How much memory does Raon-1 mini Preview (30B-A4B) need on the NVIDIA H800 80GB SXM?

At F16 it needs about 62.2 GB. The NVIDIA H800 80GB SXM has 80.0 GB usable.

How fast is Raon-1 mini Preview (30B-A4B) on the NVIDIA H800 80GB SXM?

About 113 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Raon-1 mini Preview (30B-A4B) should I use on the NVIDIA H800 80GB SXM?

F16. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.