LocalClaw/LLM/Spark-X2.5-4B
Open-weight local LLM

Spark-X2.5-4B

Catalogue summary: Spark-X2.5-4B is an Apache 2.0 compact general-purpose model from XHToken with a hybrid attention architecture, 1M-token native context, multilingual coverage and official GGUF artifacts for local llama.cpp, Ollama and LM Studio-compatible workflows.

Repository editorial metadata; verify comparative claims in the linked upstream material.

16 GB catalogue minimum16 GB RAMBF16 GGUFCoding assistant
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models
Open in LM StudioOpens the app on this model's download screenOpen in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens the model filesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
4B
Minimum RAM
16 GB
Model size
7.67 GB
Quantization
BF16 GGUF

Can Spark-X2.5-4B run locally?

Spark-X2.5-4B has a catalogue minimum of 16 GB RAM with BF16 GGUF. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use Spark-X2.5-4B as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Model sourcePublic GGUF repository (verified 2026-09-07): XHToken/Spark-X2.5-4B-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningtool-callinglong-contextgeneral

Install path

01
Check RAM fitMinimum 16 GB RAM. Start with the BF16 GGUF quant.
02
Load the modelSearch Spark-X2.5-4B in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: spark
  • Parameters: 4B
  • Recommended quantization: BF16 GGUF
  • Catalogue minimum RAM: 16 GB
  • Catalogue model size: 7.67 GB
  • Tags: chat, code, reasoning, tool-calling, long-context, general

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • reasoning
  • tool-calling
  • long-context
  • general

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
8
quality
7
coding
7
reasoning
7

Technical notes

Developer
XHToken / SparkLLM
License
Apache 2.0
Context window
1,048,576 tokens
Architecture
Compact 4B Spark-X2.5 causal language model with a hybrid attention design that combines full-attention and sliding-window attention layers for lower long-context overhead.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Starter desktopMac mini M4 16GBPortable fitMacBook Air M4 16GBBest 16GB models16GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Spark-X2.5-1.7B 1.7BMiniCPM5 2B 2BNemotron 3.5 Lightning 30B-A3B 30B (3B active, MoE)Ornith-1.5-9B 9BAgents-A1 4B 4BGranite 4.2 (3B) 3BGranite 4.2 (8B) 8.8BK2-Horizon-0.9B 0.9B

Where to go next