What are the hardware requirements for A.X K2 DSpark?

A.X K2 DSpark requires approximately 6.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed A.X K2 DSpark and how large is it?

A.X K2 DSpark is developed by skt, a model with 3.4b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate A.X K2 DSpark?

A.X K2 DSpark is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

A.X K2 DSpark by skt — VRAM 6.8GB

Name: A.X K2 DSpark
Author: skt

A.X K2 DSpark is an open-source language model by skt. Features: 3.4b LLM, VRAM: 6.8GB, License: apache-2.0, LLM Explorer Score: 0.31.

Arxiv:2607.05147 Axk2 Base model:finetune:skt/a.x-k2 Base model:skt/a.x-k2 Custom code Draft-model Dspark En Ko Region:us Safetensors Speculative-decoding Vllm

Model Card on HF 🤗: https://huggingface.co/skt/A.X-K2-DSpark

A.X K2 DSpark Parameters and Internals

LLM Name	A.X K2 DSpark
Repository 🤗	https://huggingface.co/skt/A.X-K2-DSpark
Base Model(s)	skt/A.X-K2 skt/A.X-K2
Model Size	3.4b
Required VRAM	6.8 GB
Updated	2026-08-15
Maintainer	skt
Model Files	6.8 GB
Supported Languages	en ko
Model Architecture	DSparkDraftModel
License	apache-2.0
Transformers Version	5.14.1

Rank the A.X K2 DSpark capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation