Spark X2.5 4B

Spark X2.5 4B from XHToken. Source-based hardware guidance from its published configuration.

EstimatedRepository opened Aug 24, 2026Source checked 9/24/2026Version: 0bcb3567

LOCALRENTED GPUOPEN WEIGHTS

At a glance

Parameters: 4.11B
Architecture: spark2_5
Context length: 1,048,576
License: apache-2.0
Disk space: 7.7 GB
Software: Ollama, SGLang, vLLM

View the model source

MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

MODEL-SPECIFIC SETUPS

Run it your way

Choose what you want to do with Spark X2.5 4B. Each guide uses this model’s own files and runtime.

Private chatSet up private chat with Spark X2.5 4BInstall Ollama, pull the Spark X2.5 4B model, and verify that a local prompt returns a model response. Ollama's native spark2_5 support requires v0.34.1 or later.Open setup CodingBuild a local coding assistant with Spark X2.5 4BRun Spark X2.5 4B locally with Ollama and use it as a coding assistant for a small, reviewable code task. The guide installs the runtime, pulls the exact publisher-published model, launches an interactive session, and verifies the model's output on a concrete coding request.Open setup

Ways to run it

Ollama · Windows, macOS, Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

ollama run SparkLLM/Spark-X2.5-4B

Official instructions

SGLang · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

python -m sglang.launch_server  --model-path /root/Spark-X2.5-4B  --served-model-name spark2.5  --tool-call-parser spark25  --reasoning-parser qwen3  --tp-size 1  --mem-fraction-static 0.8  --context-length 1048576  --chat-template /root/Spark-X2.5-4B/chat_template.jinja  --host 0.0.0.0  --port 30000

Official instructions

vLLM · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

vllm serve "/models/Spark-X2.5-4B"  --port "30000"  --trust-remote-code  --served-model-name spark25  --tensor-parallel-size 1  --gpu-memory-utilization 0.7  --enable-prefix-caching  --chat-template /models/Spark-X2.5-4B/chat_template.jinja

Official instructions

Explore its uses

SAFETENSORSTEXT-GENERATION

Keep exploring

Text

Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

MODEL SIZE27.36B

LOCALRENTED GPU

Released Sep 17, 2026

Text

DeepSeek

DeepSeek V4.1 Flash

A multimodal reasoning model with a compressed key-value cache, published as open weights.

LOCALRENTED GPU

Repository opened Sep 10, 2026

Text

Qwen

Qwen3.8-Flash-Next

An experimental open-weight multimodal model with sparse attention and 262K native context.

MODEL SIZE125B language · 6B active

LOCALRENTED GPU

Repository opened Aug 24, 2026