What are the hardware requirements for Xspark X2.6 Math?

Xspark X2.6 Math requires approximately 8.2 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Xspark X2.6 Math and how large is it?

Xspark X2.6 Math is developed by arcticoneai, a model with 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 Xspark X2.6 Math?

Xspark X2.6 Math is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Xspark X2.6 Math by arcticoneai — VRAM 8.2GB, 1024K context

Name: Xspark X2.6 Math
Author: arcticoneai

Xspark X2.6 Math is an open-source language model by arcticoneai. Features: 4b LLM, VRAM: 8.2GB, Context: 1024K, License: other, LLM Explorer Score: 0.34.

4b Base model:finetune:xhtoken/sp... Base model:xhtoken/spark-x2.6-... Conversational Custom code Distillation En Experimental Lean4 Lora Lora-merged Math Mathematical-reasoning Mathematics Reasoning Region:us Safetensors Sharded Spark2 5 Tensorflow

Model Card on HF 🤗: https://huggingface.co/arcticoneai/xspark-X2.6-math

Xspark X2.6 Math Parameters and Internals

LLM Name	Xspark X2.6 Math
Repository 🤗	https://huggingface.co/arcticoneai/xspark-X2.6-math
Base Model(s)	XHToken/Spark-X2.6-4B XHToken/Spark-X2.6-4B
Model Size	4b
Required VRAM	8.2 GB
Updated	2026-11-11
Maintainer	arcticoneai
Model Type	spark2_5
Model Files	5.0 GB: 1-of-2 3.2 GB: 2-of-2
Supported Languages	en
Model Architecture	Spark2_5ForCausalLM
License	other
Context Length	1048576
Model Max Length	1048576
Transformers Version	4.57.6
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<｜▁pad▁｜>
Vocabulary Size	131072
LoRA Model	Yes

Rank the Xspark X2.6 Math 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

Best Alternatives to Xspark X2.6 Math

Best Alternatives	Context / RAM	Downloads	Likes
Spark X2.6 4B	1024K / 8.3 GB	2537	440
Laplace 1 Vector	1024K / 8.3 GB	3057	42
Spark X2.6 4B Base	1024K / 8.3 GB	433	30
Spark X2.6 4B HTML	1024K / 8.2 GB	780	2
Spark X2.6 4B FP8	1024K / 4.5 GB	391	23
Spark X2.6 4B INT8	1024K / 4.5 GB	432	21
Spark X2.6 4B ONNX WebGPU	1024K / GB	949	1
Spark X2.5 4B	1024K / 8.3 GB	429	106
Spark X2.6 4B INT4	1024K / 3.4 GB	208	15
Lucet CoderV6 4B Omega	1024K / 0.1 GB	421	1

Note: green Score (e.g. "73.2") means that the model is better than arcticoneai/xspark-X2.6-math.