AI Rank
中文
← Open Source
GradientHQ

parallax

Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere.

InfrastructureDeploy & ServeOrchestrationPython
Open on GitHub
Momentum
+0stars in 24 hours0.0%
1.40k
Stars
150
Forks
+0
This week
26
Contributors
Created 2025-09-22 · Updated 2026-10-15 · #10462 today
Top developers
gufengcTianyiZhao1437sl-gn

GradientHQ/parallax is ranked 10,462 with 1,397 stars.

Same-category comparison

GradientHQ/parallax is ranked 10,462 among these 8 peers; doonny/PipeCNN is ranked 10,474.

Same-category comparison
NameRankMetrics
sauravpanda/BrowserAI10,303
Language:
TypeScript
Stars:
1,449
Forks:
139
Description:
Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser.
deepseek-ai/EPLB10,309
Language:
Python
Stars:
1,447
Forks:
211
Description:
Expert Parallelism Load Balancer.
kitops-ml/kitops10,356
Language:
Go
Stars:
1,430
Forks:
186
Description:
An open source DevOps tool from the CNCF for packaging and versioning AI/ML models, datasets, code, and configuration into an OCI Artifact.
cloudposse/atmos10,445
Language:
Go
Stars:
1,402
Forks:
189
Description:
👽 Terraform Orchestration Tool for DevOps. Keep environment configuration DRY with hierarchical imports of configurations, inheritance, and WAY more. Native support for Terraform and Helmfile.
doonny/PipeCNN10,474
Language:
C
Stars:
1,393
Forks:
373
Description:
An OpenCL-based FPGA Accelerator for Convolutional Neural Networks.
algolia/algoliasearch-client-javascript10,511
Language:
TypeScript
Stars:
1,383
Forks:
226
Description:
⚡️ A fully-featured and blazing-fast JavaScript API client to interact with Algolia.
linweiyuan/go-chatgpt-api10,516
Language:
Go
Stars:
1,381
Forks:
406
tensorflow/ecosystem10,519
Language:
Scala
Stars:
1,377
Forks:
388
Description:
Integration of TensorFlow with other open-source frameworks.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryInfrastructure
SubcategoryDeploy & Serve, Orchestration
KeywordsDistributed
Stars1,397
Forks150
Contributors26
Created date2025-09-22
Updated date2026-10-15
Stars in 1 day0
Stars in 7 days0
Rank10,462
Previous rank10,457
Rank change-5
7-day stars rank12,632
Previous 7-day stars rank12,664
7-day stars rank change32
Total stars rank8,577
Previous total stars rank8,567
Total stars rank change-10
README summary

**Gradient** | **Blog** | **X/Twitter (Gradient)** | **X/Twitter (Parallax)** | **Discord** | **Arxiv** News [2026/02] 🦞 Parallax now supports OpenClaw integration! See Docs [2025/10] 🔥 Parallax won #1 Product of The Day on Product Hunt! About A fully decentralized inference engine developed by Gradient. Parallax lets you build your own AI cluster for model inference onto a set of distributed nodes despite their varying configuration and physical location. Its core features include: **Host local LLM on personal devices** **Cross-platform support** **Pipeline parallel

model sharding** **Paged KV cache management & continuous batching for Mac** **Dynamic request scheduling and routing for high performance** The backend architecture: P2P communication powered by Lattica GPU backend powered by SGLang and vLLM Mac backend powered by MLX LM User Guide Installation Getting Started Working with OpenClaw 🦞 Quick Install Contributing We warmly welcome contributions of all kinds! For guidelines on how to get involved, please refer to our Contributing Guide. 2 is built for stronger reasoning and agent workflows, adding

thinking-aware tool use while keeping both thinking and non-thinking tool-use modes available. 7 | MiniMax M3: Frontier Coding, 1M Context, Native Multimodality | MiniMax-M3 is a sparse-attention model for coding, agentic work, long-context tasks, and multimodal input, with MiniMax-M2. 2: Built for Long-Horizon Tasks | GLM-5. 2 is Z AI's latest flagship model for long-horizon coding agents, large-scale implementation, automated research, and performance optimization. | |Kimi-K2 | Moonshot AI | Kimi-K2-Thinking Kimi

-K2-Instruct-0905 | Kimi K2 Thinking | Kimi-K2-Thinking is the reasoning-focused Kimi-K2 variant for long-horizon agentic workflows, multi-step reasoning, and tool-heavy tasks. 6-35B-A3B: Agentic Coding Power, Now Open to All | Qwen3. 6-35B-A3B is an open-weight MoE model focused on stable, practical coding and agentic workflows, with Qwen3-Next and larger Qwen3 MoE variants also represented. | |gpt-oss | OpenAI | gpt-oss-120b gpt-oss-safeguard-120b | Introducing gpt-oss-safeguard

| gpt-oss-120b is OpenAI's open-weight GPT model; gpt-oss-safeguard-120b adds policy-driven reasoning classification for flexible moderation and safety workflows. 5-Flash is a sparse MoE foundation model for efficient reasoning and agentic workflows, activating a small subset of its total parameters per token.

Frequently asked questions

How many stars and forks are recorded?

GradientHQ/parallax has 1,397 stars and 150 forks.

What is the repository rank?

GradientHQ/parallax is ranked 10,462.

What language and category are recorded?

GradientHQ/parallax has 1,397 stars, uses Python and belongs to Infrastructure.

Which repository is closest in rank?

GradientHQ/parallax is compared with doonny/PipeCNN, ranked 10,474 with 1,393 stars.

README
 ![](docs/images/parallax.png)

Trusted by Partners

   ![SGLang](docs/images/sglang.png) 
   ![vLLM](docs/images/vllm.png) 
   ![Qwen](docs/images/qwen.avif) 
   ![DeepSeek](docs/images/deepseek.png) 
   ![Kimi](docs/images/kimi.png) 
   ![Minimax](docs/images/minimax.png) 
   ![ZAI](docs/images/zai.svg)

Gradient | Blog | X/Twitter (Gradient) | X/Twitter (Parallax) | Discord | Arxiv

News

  • [2026/02] 🦞 Parallax now supports OpenClaw integration! See Docs
  • [2025/10] 🔥 Parallax won #1 Product of The Day on Product Hunt!
  • [2025/10] 🔥 Parallax version 0.0.1 has been released!

About

A fully decentralized inference engine developed by Gradient. Parallax lets you build your own AI cluster for model inference onto a set of distributed nodes despite their varying configuration and physical location. Its core features include:

  • Host local LLM on personal devices
  • Cross-platform support
  • Pipeline parallel model sharding
  • Paged KV cache management & continuous batching for Mac
  • Dynamic request scheduling and routing for high performance

The backend architecture:

User Guide

Quick Install

git clone https://github.com/GradientHQ/parallax.git
cd parallax
./install.sh
source .venv/bin/activate
parallax serve -m Qwen/Qwen3.5-0.8B

Contributing

We warmly welcome contributions of all kinds! For guidelines on how to get involved, please refer to our Contributing Guide.

Supported Models

Provider HuggingFace Collection Blog Description
DeepSeek Deepseek DeepSeek-V3.2
DeepSeek-R1
DeepSeek-V3.2 Release DeepSeek-V3.2 is built for stronger reasoning and agent workflows, adding thinking-aware tool use while keeping both thinking and non-thinking tool-use modes available.
MiniMax MiniMax AI MiniMax-M3
MiniMax-M2.7 MiniMax M3: Frontier Coding, 1M Context, Native Multimodality MiniMax-M3 is a sparse-attention model for coding, agentic work, long-context tasks, and multimodal input, with MiniMax-M2.7 kept as a supported sibling model.
GLM Z AI GLM-5.2
GLM-5.1
GLM-4.7 GLM-5.2: Built for Long-Horizon Tasks GLM-5.2 is Z AI's latest flagship model for long-horizon coding agents, large-scale implementation, automated research, and performance optimization.
Kimi-K2 Moonshot AI Kimi-K2-Thinking
Kimi-K2-Instruct-0905 Kimi K2 Thinking Kimi-K2-Thinking is the reasoning-focused Kimi-K2 variant for long-horizon agentic workflows, multi-step reasoning, and tool-heavy tasks.
Qwen Qwen Qwen3.6-35B-A3B Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All Qwen3.6-35B-A3B is an open-weight MoE model focused on stable, practical coding and agentic workflows, with Qwen3-Next and larger Qwen3 MoE variants also represented.
gpt-oss OpenAI gpt-oss-120b
gpt-oss-safeguard-120b Introducing gpt-oss-safeguard gpt-oss-120b is OpenAI's open-weight GPT model; gpt-oss-safeguard-120b adds policy-driven reasoning classification for flexible moderation and safety workflows.
Step StepFun Step-3.5-Flash Step 3.5 Flash Step-3.5-Flash is a sparse MoE foundation model for efficient reasoning and agentic workflows, activating a small subset of its total parameters per token.
Nearby in the ranking
Similar items