What are the hardware requirements for Spark X2.5 4B FP8?

Spark X2.5 4B FP8 requires approximately 4.4 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 Spark X2.5 4B FP8 and how large is it?

Spark X2.5 4B FP8 is developed by XHToken, 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 Spark X2.5 4B FP8?

Spark X2.5 4B FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Spark X2.5 4B FP8 by XHToken — VRAM 4.4GB, 1024K context

Name: Spark X2.5 4B FP8
Author: XHToken

Spark X2.5 4B FP8 is an open-source language model by XHToken. Features: 4b LLM, VRAM: 4.4GB, Context: 1024K, License: apache-2.0, LLM Explorer Score: 0.26.

Base model:quantized:xhtoken/s... Base model:xhtoken/spark-x2.5-... Conversational Custom code Fp8 Region:us Safetensors Sharded Spark2 5 Sparkx2 5 Tensorflow

Model Card on HF 🤗: https://huggingface.co/XHToken/Spark-X2.5-4B-FP8

Spark X2.5 4B FP8 Parameters and Internals

LLM Name	Spark X2.5 4B FP8
Repository 🤗	https://huggingface.co/XHToken/Spark-X2.5-4B-FP8
Base Model(s)	XHToken/Spark-X2.5-4B-Base XHToken/Spark-X2.5-4B-Base
Model Size	4b
Required VRAM	4.4 GB
Updated	2026-09-06
Maintainer	XHToken
Model Type	spark2_5
Model Files	1.3 GB: 1-of-5 1.0 GB: 2-of-5 1.0 GB: 3-of-5 1.0 GB: 4-of-5 0.1 GB: 5-of-5
Model Architecture	Spark2_5ForCausalLM
License	apache-2.0
Context Length	1048576
Model Max Length	1048576
Transformers Version	4.57.1
Tokenizer Class	PreTrainedTokenizerFast
Beginning of Sentence Token	<｜start▁of▁sentence｜>
End of Sentence Token	<｜end▁of▁sentence｜>
Unk Token	<unk>
Vocabulary Size	131072

Rank the Spark X2.5 4B FP8 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 Spark X2.5 4B FP8

Best Alternatives	Context / RAM	Downloads	Likes
Spark X2.6 4B	1024K / 8.3 GB	2537	440
Spark X2.6 4B Base	1024K / 8.3 GB	433	30
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 X2.6 4B INT4	1024K / 3.4 GB	208	15
Spark X2.6 4B AgentFast	1024K / 8.2 GB	397	0
Spark X2.5 4B	1024K / 8.3 GB	429	106
Spark X2.5 4B Japanese	1024K / 8.2 GB	1912	1
Spark X2.6 4B Abliterated	1024K / 8.2 GB	123	0

Note: green Score (e.g. "73.2") means that the model is better than XHToken/Spark-X2.5-4B-FP8.