XHToken/Spark-X2.5-4B-GGUF overview
Spark X2.5 4B GGUF Spark X2.5 is a compact, general purpose language model for conversation, writing, translation, reasoning, coding, tool use, and agentic wor…
Runs locally from ~2.42 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | XHToken/Spark-X2.5-4B-GGUF |
|---|---|
| Author | XHToken |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | XHToken/Spark-X2.5-4B |
| Last modified | 2026-09-20T08:08:37.000Z |
Model README
---
license: apache-2.0
language:
- en
- zh
library_name: gguf
pipeline_tag: text-generation
base_model: XHToken/Spark-X2.5-4B
tags:
- gguf
- llama.cpp
- ollama
- lm-studio
- sparkx2_5
- unsloth
- pocketpal-ai
---
Spark-X2.5-4B-GGUF
Spark-X2.5 is a compact, general-purpose language model for conversation, writing, translation, reasoning, coding, tool use, and agentic workflows. It uses a hybrid attention architecture, supports a native context length of up to 1M tokens, and covers more than 200 languages. For its architecture, training methods, benchmark results, fine-tuning, and citation, see the Spark-X2.5-4B.
Local Deployment
llama.cpp
> [!NOTE]
> Native spark2_5 support requires llama.cpp b10828 or later.
Run the model in the CLI:
llama cli -m /path/to/Spark-X2.5-4B-GGUFLaunch the OpenAI-compatible API server:
llama serve -m /path/to/Spark-X2.5-4B-GGUFOllama
> [!NOTE]
> Native spark2_5 support requires Ollama v0.34.1 or later.
ollama run SparkLLM/Spark-X2.5-4BLM Studio
> [!NOTE]
> Native spark2_5 support requires runtime version 2.34.0 or later.
Unsloth
> [!NOTE]
> The latest Unsloth Studio supports native Spark-X2.5 GGUF inference.
License
Released under the Apache License 2.0.
Run XHToken/Spark-X2.5-4B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models