A.X-K2
KRAFTONcc-by-nc-4.0audio

A.X-K2

Updated Sep 28, 2026
Parameters
21.2B
Context
8,192
License
cc-by-nc-4.0
Updated
Sep 28, 2026

Intelligence benchmarks

Artificial Analysis indexes - compared with the best open and proprietary models

Intelligence

22.7

AA Index

Coding

38.8

AA Index

Intelligence Index - A.X-K2 vs. the field

Best open-weight models (you can run locally) and leading proprietary models for context.

Claude Opus 5.5
57.6
closed
Claude Fable 5.1
53.4
closed
GPT-6 Astra
52.7
closed
Muse Spark 1.3
48.1
closed
GPT-6 Sol
47.5
closed
MiMo-V2.6-Pro
46.3
open
GLM-5.3
44.8
open
A.X-K2
22.7
open

Coding Index comparison

Claude Fable 5.1
81.6
closed
GPT-6 Astra
77.1
closed
Grok 4.6
76.8
closed
GPT-5.6 Terra
76.7
closed
Muse Spark 1.3
76.5
closed
Kimi K3
76.2
open
GLM-5.3
74.8
open
A.X-K2
38.8
open

Benchmark data from Artificial Analysis · updated 2026-09-28.

Standard benchmarks

Performance across standard evaluations

BenchmarkScore
GPQA Diamond85.7
HLE29.6
SciCode41

Source: Artificial Analysis component evals - updated 2026-09-28.

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at Q5_K_M
2 of 4 quantizations fit A.X-K2 with real runtime overhead.
Q4_K_M
12 GB
Q5_K_M
15 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve KRAFTON/A.X-K2-Raon-Speech-21B-A3B

New 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. It scores 22.7 on the Artificial Analysis Intelligence Index. At Q4_K_M it needs roughly 12 GB of VRAM, placing it in the 8–12 GB GPU hardware tier.

Benchmarks

Artificial Analysis Intelligence Index - A.X-K2 vs. leading closed models:

ModelIntelligenceCodingGPQA
A.X-K235-85.7
Claude Opus 5 (max)63.1-93.2
Claude Fable 5 (with fallback)62.1-92.6
GPT-5.6 Sol (max)60.9-94.1
Grok 4.6 (high)60.9-94.9
Qwen3.8 Max58.1-92.7

Source: Artificial Analysis (2026-08-13).

Popularity

A.X-K2 has 5,454 downloads in the last month on HuggingFace and 96 likes.

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 general use.

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