Together AI
Inference and fine-tuning platform for open-source LLMs.
Large Language Models · LLM Tools & Frameworks
Browser-based calculator that estimates the GPU memory an LLM needs for inference or fine-tuning (weights, KV cache and overhead) from the model's Hugging Face config, and lists the GPUs and Macs that fit.
This page shows only what the catalog has recorded about ModelVRAM. Missing details are marked “Not recorded”. Check the official site for current pricing and availability before choosing a tool for real work.
Added on 29 sept. 2026 as a catalog migration. A recorded date shows when the entry was added. It is not independent verification of pricing, availability or product claims.
{
"name": "ModelVRAM",
"url": "https://modelvram.com/",
"description": "Browser-based calculator that estimates the GPU memory an LLM needs for inference or fine-tuning (weights, KV cache and overhead) from the model's Hugging Face config, and lists the GPUs and Macs that fit.",
"category": "large-language-models",
"subcategory": {
"id": "llm-tools-and-frameworks",
"name": "LLM Tools & Frameworks"
},
"pricing": "free",
"openSource": null,
"status": "listed",
"source": {
"kind": "readme-migration",
"migratedAt": "2026-09-29"
}
}Same type first, then other tools in Large Language Models. Order follows shared wording in the catalog descriptions.
Inference and fine-tuning platform for open-source LLMs.
ML model hub with models, datasets, and Inference Endpoints.
Framework for building LLM applications with chains, agents, and memory.
Run LLMs locally with simple CLI and model library.
Unified OpenAI-compatible API gateway and browser playground for text, image, video, and voice models.
Data framework for LLM applications with RAG and data connectors.
0 / 3
Compare