Aiqre

Model library / XHToken

Spark-X2.5-1.7B-Base

Spark-X2.5-1.7B-Base is a 1.7 billion-parameter general-purpose language model with a native 1 M-token context window.

1.7B

Parameters in total

1,048,576

Context length in tokens, as published

3 GiB

Weights at the released precision

apache-2.0

Licence declared on the repository

Overview

What this model is.

The model is a compact, general-purpose LLM released by XHToken. According to the publisher it targets everyday tasks such as conversation, writing, translation, reasoning, coding, tool use and agentic workflows, supporting over 200 languages. Its architecture combines a full-attention layer with three sliding-window layers to reduce computational overhead while maintaining long-context capability.

In practice the model comprises 1.7 billion parameters using the Spark2_5ForCausalLM architecture without expert layers. It accepts up to 1,048,576 tokens of context, is distributed in bfloat16 format and is covered by the Apache-2.0 licence. The repository provides weights and configuration files compatible with major inference frameworks and hardware platforms.

Specification

The published shape.

RepositoryXHToken/Spark-X2.5-1.7B-Base
PublisherXHToken
Published28 August 2026
ArchitectureSpark2_5ForCausalLM
Model typespark2_5
Parameters1,707,657,216
Layers28
Hidden size2,048
Attention heads8, 2 key/value heads
Context length1,048,576 tokens
Vocabulary131,072 tokens
Weight formatbfloat16
Licenceapache-2.0

Memory

How much VRAM the weights need.

Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.

PrecisionWeightsNotes
bf163.2 GiBFull precision as released
fp81.6 GiB8-bit, near-lossless on most models
int40.8 GiB4-bit, smallest footprint

The cache costs 56 KiB per token at 16-bit, so the full 1,048,576-token context of one request needs about 56.0 GiB. Concurrency multiplies that number, not the weights.

That figure is an upper bound: this model uses sliding-window attention with a 512-token window on some layers, so long requests cache less than this.

Hardware

Which card runs it.

At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.

GPUCards neededFree for cacheContext it holds
RTX 4090 24GB 1 15.9 GiB about 298,080 tokens
RTX 5090 32GB 1 23.1 GiB about 432,897 tokens
L40S 48GB 1 37.5 GiB about 702,531 tokens
A100 80GB 1 66.3 GiB the full 1,048,576 tokens
H100 80GB 1 66.3 GiB the full 1,048,576 tokens
RTX PRO 6000 96GB 1 80.7 GiB the full 1,048,576 tokens
H200 141GB 1 121.2 GiB the full 1,048,576 tokens

Serving

Running it yourself.

A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.

vllm serve XHToken/Spark-X2.5-1.7B-Base \
  --max-model-len 294912 \
  --gpu-memory-utilization 0.90

Questions

The things people ask about this model.

How much GPU memory does Spark-X2.5-1.7B-Base need?

The weights take about 3 GiB at the released precision. That fits on one RTX 4090 24GB, which leaves roughly 16 GiB for the key-value cache.

What licence does Spark-X2.5-1.7B-Base use?

The repository declares apache-2.0. Read the licence text before commercial use: the name alone does not tell you what is allowed.

How long a context does it support?

The configuration allows 1,048,576 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.

Can I use it through an API instead of hosting it?

This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.

Also in the library

Related models.

XHToken/Spark-X2.5-4B-Base

Spark-X2.5-4B is a 4.1 billion-parameter causal language model from XHToken designed for general-purpose tasks with a 1 M token c…

XHToken/Spark-X2.5-4B

Spark-X2.5-4B is a 4.1-billion-parameter causal language model with a 1-million-token context window, released under Apache-2.0.

XHToken/Spark-X2.5-1.7B

Spark-X2.5-1.7B is a 1.7 billion-parameter causal language model from XHToken with a 1 M token context window, released under Apa…

openbmb/MiniCPM5-2B

MiniCPM5-2B is a 2-billion-parameter dense transformer aimed at on-device and resource-constrained deployments.

Hosting

Want this model on a dedicated EU GPU?

Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.