A.X-K2
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| GPQA Diamond | 85.7 |
| HLE | 29.6 |
| SciCode | 41 |
Source: Artificial Analysis component evals - updated 2026-11-12.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve KRAFTON/A.X-K2-Raon-Speech-21B-A3BNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
A.X-K2 is a 21.2B-parameter cc-by-nc-4.0 model from SK Telecom. At Q4_K_M it needs roughly 12 GB of VRAM, placing it in the 8–12 GB GPU hardware tier.
PopularityLink to this section
A.X-K2 has 5,454 downloads in the last month on HuggingFace and 96 likes.
From the community
What users are saying
“Hi Poli, thank you for confirming and for transferring the Space to the KRAFTON organization! We really appreciate you putting the demo together. We'll review the Space, make any necessary adjustments, and look into linking it from the model card and related repositories.”
“Hi KRAFTON team — congratulations on the release, and thank you for opening the weights. We tested the Korean output and it is the most natural Korean speech we have heard from an open model.”
“Hi Poli, thanks so much for putting this together - the demo looks great! We’d be happy to have it transferred to the KRAFTON organization.”
Frequently asked
Quick answers to common questions
How much VRAM does A.X-K2 need?
A.X-K2 with 21.2B parameters needs approximately 12 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is A.X-K2 better than other KRAFTON models?
A.X-K2 has 21.2B parameters with 8,192 context - a strong choice for multimodal, general-chat.
What license is A.X-K2 under?
A.X-K2 is released under the cc-by-nc-4.0 license, making it suitable for most commercial and personal projects.
What hardware runs A.X-K2 well?
With 21.2B parameters, A.X-K2 requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for A.X-K2?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~15 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
What models compete with A.X-K2?
A.X-K2 competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec