RankLLM

RankLLM

Castorini
RankLLM oMLX

Related Products

  • Gemini platform
    4.3 out of 5 stars 1,178 Ratings
    Visit Website for Gemini platform
  • QA Wolf
    4.8 out of 5 stars 284 Ratings
    Visit Website for QA Wolf
  • LTX
    4.4 out of 5 stars 182 Ratings
    Visit Website for LTX
  • SearchUnify
    4.5 out of 5 stars 150 Ratings
    Visit Website for SearchUnify
  • LM-Kit.NET
    4.8 out of 5 stars 29 Ratings
    Visit Website for LM-Kit.NET
  • AddSearch
    4.6 out of 5 stars 145 Ratings
    Visit Website for AddSearch
  • RallyFuel
    5.0 out of 5 stars 1 Rating
    Visit Website for RallyFuel
  • kama.ai
    4.8 out of 5 stars 9 Ratings
    Visit Website for kama.ai
  • LogicalDOC
    4.5 out of 5 stars 151 Ratings
    Visit Website for LogicalDOC
  • Buildium
    4.5 out of 5 stars 2,563 Ratings
    Visit Website for Buildium
RankLLM:

About

RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking. It offers a suite of rerankers, pointwise models like MonoT5, pairwise models like DuoT5, and listwise models compatible with vLLM, SGLang, or TensorRT-LLM. Additionally, it supports RankGPT and RankGemini variants, which are proprietary listwise rerankers. It includes modules for retrieval, reranking, evaluation, and response analysis, facilitating end-to-end workflows. RankLLM integrates with Pyserini for retrieval and provides integrated evaluation for multi-stage pipelines. It also includes a module for detailed analysis of input prompts and LLM responses, addressing reliability concerns with LLM APIs and non-deterministic behavior in Mixture-of-Experts (MoE) models. The toolkit supports various backends, including SGLang and TensorRT-LLM, and is compatible with a wide range of LLMs.
oMLX:

About

oMLX is a macOS-native MLX server designed to make local AI faster and more practical on Apple Silicon. Built for the way coding agents actually work, it uses paged SSD KV caching to persist cache blocks to disk, allowing previously seen prefixes to be restored across requests and server restarts instead of being recomputed from scratch. This can reduce time to first token on long contexts from 30–90 seconds to under five seconds after the first turn. Continuous batching handles concurrent requests through mlx-lm’s BatchGenerator, improving generation throughput without forcing requests to wait behind a single job. oMLX can serve LLMs, vision-language models, embedding models, and rerankers simultaneously, using LRU eviction when memory runs low. It supports any MLX-format model from Hugging Face, including Qwen, LLaMA, Mistral, Gemma, DeepSeek, MiniMax, and GLM, and can reuse models already stored in the standard Hugging Face cache, LM Studio folders, or custom directories.
RankLLM:

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported
oMLX:

Platforms Supported

Windows Not Supported
Mac Supported
Linux Not Supported
Cloud Not Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported
RankLLM:

Audience

Academic researchers and developers seeking a solution offering tools for implementing and evaluating listwise reranking with large language models
oMLX:

Audience

Developers and AI power users needing to run fast local LLM inference and agentic coding workflows on Apple Silicon
RankLLM:

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported
oMLX:

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported
RankLLM:

API

Offers API Supported
oMLX:

API

Offers API Supported
RankLLM:

Screenshots and Videos

oMLX:

Screenshots and Videos

RankLLM:

Pricing

Free
Free Version Supported
Free Trial Not Supported
oMLX:

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported
RankLLM:

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software
oMLX:

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software
RankLLM:

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported
oMLX:

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported
RankLLM:

Company Information

Castorini
Canada
github.com/castorini/rank_llm/
oMLX:

Company Information

oMLX
United States
omlx.ai/
RankLLM:

Alternatives

RankGPT

RankGPT

Weiwei Sun
oMLX:

Alternatives

Photon

Photon

Moondream
RankLLM:
ColBERT

ColBERT

Future Data Systems
oMLX:
Run BiOS

Run BiOS

UltraSafe AI Inc.
RankLLM:
oMLX:
Macyou

Macyou

Macyou LLC
RankLLM:
oMLX:
BaseRT

BaseRT

Base Compute
RankLLM:
oMLX:
RankLLM:

Categories

Reranking Models Supported
oMLX:

Categories

AI Inference Supported
RankLLM:

Integrations

Llama Supported
Mistral AI Supported
OpenAI Supported
Python Supported
Qwen Supported
Claude Code Not Supported
Cursor Not Supported
DeepSeek Not Supported
GLM-4.1V Not Supported
Gemini Supported
Gemini Enterprise Supported
Gemma Not Supported
Gemma Not Supported
GitHub Not Supported
Hugging Face Not Supported
JSON Not Supported
LM Studio Not Supported
MiniMax Not Supported
Model Context Protocol (MCP) Not Supported
OpenClaw Not Supported
oMLX:

Integrations

Llama Supported
Mistral AI Supported
OpenAI Supported
Python Supported
Qwen Supported
Claude Code Supported
Cursor Supported
DeepSeek Supported
GLM-4.1V Supported
Gemini Not Supported
Gemini Enterprise Not Supported
Gemma Supported
Gemma Supported
GitHub Supported
Hugging Face Supported
JSON Supported
LM Studio Supported
MiniMax Supported
Model Context Protocol (MCP) Supported
OpenClaw Supported
RankLLM:
Claim RankLLM and update features and information
Claim RankLLM and update features and information
oMLX:
Claim oMLX and update features and information
Claim oMLX and update features and information