RankLLMCastorini
|
Recursive FlintRecursive
|
|||||
| RankLLM | Recursive Flint | |||||
|---|---|---|---|---|---|---|
Related Products
|
||||||
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.
|
Recursive Flint:
About
Recursive Flint is a 40-billion-parameter mixture-of-experts language model for agentic coding on local hardware. It activates about 2.5 billion parameters per token and supports reasoning, multi-turn tool use, and context windows up to 512,000 tokens. Developers can use Flint with coding agents to inspect codebases, fix bugs, implement features, and write tests while running inference on their own hardware. Its weights are published under the Apache 2.0 license. Flint works with llama.cpp, Ollama, Unsloth, LM Studio, vLLM, and SGLang; Recursive also provides rec, an inference engine optimized for Apple Silicon M4 Pro and M5 Pro/Max. Setup documentation and examples help developers run the model locally. Flint is for developers and technical teams that want to operate and adapt a code-focused model on their own systems.
|
|||||
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
|
Recursive Flint:
Platforms Supported
Windows
Not Supported
Mac
Supported
Linux
Not Supported
Cloud
Supported
On-Premises
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
|
Recursive Flint:
Audience
Software developers and technical teams building or using coding agents, especially those seeking to run a coding model locally.
|
|||||
RankLLM:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
Recursive Flint:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Not Supported
|
|||||
RankLLM:
API
Offers API
Supported
|
Recursive Flint:
API
Offers API
Supported
|
|||||
RankLLM:
Screenshots and Videos |
Recursive Flint:
Screenshots and VideosNo images available
|
|||||
RankLLM:
Pricing
Free
Free Version
Supported
Free Trial
Not Supported
|
Recursive Flint:
Pricing
No information available.
Free Version
Supported
Free Trial
Not Supported
|
|||||
RankLLM:
Reviews/
|
Recursive Flint:
Reviews/
|
|||||
RankLLM:
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
Recursive Flint:
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
RankLLM:
Company InformationCastorini
Canada
github.com/castorini/rank_llm/
|
Recursive Flint:
Company InformationRecursive
Founded: 2026
United States
recursive.com/updates/introducing-recursive-flint
|
|||||
RankLLM:
Alternatives |
Recursive Flint:
Alternatives |
|||||
|
RankLLM:
|
Recursive Flint:
|
|||||
|
RankLLM:
|
Recursive Flint:
|
|||||
|
RankLLM:
|
Recursive Flint: | |||||
| RankLLM: |
Recursive Flint:
|
|||||
RankLLM:
Categories |
Recursive Flint:
Categories |
|||||
RankLLM:
Integrations
Gemini
Supported
Gemini Enterprise
Supported
LM Studio
Not Supported
Llama
Supported
Mistral AI
Supported
NVIDIA TensorRT
Supported
Ollama
Not Supported
OpenAI
Supported
OpenRouter
Not Supported
Python
Supported
|
Recursive Flint:
Integrations
Gemini
Not Supported
Gemini Enterprise
Not Supported
LM Studio
Supported
Llama
Not Supported
Mistral AI
Not Supported
NVIDIA TensorRT
Not Supported
Ollama
Supported
OpenAI
Not Supported
OpenRouter
Supported
Python
Not Supported
|
|||||
|
RankLLM:
|
Recursive Flint:
|