GPU Inference Memory Calculator Connector for AI agents.
4 live capabilities
Plan your VRAM requirements and batch capacities for LLM deployment
Waiting for input…
Why people use GPU Inference Memory Calculator
GPU Inference Memory Calculator for Accurate LLM Hardware Planning
This Connector changes that by doing the math for you. You just tell your agent the model specs and your hardware limits, and it gives you the numbers. You get a clear plan for your deployment without the headache of manual formulas.
What Vinkius changes
You get accurate hardware requirements for LLM deployment without doing the math yourself.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Checking if a 70B model fits on a 24GB card
A developer asks their agent if a specific model will run on a consumer GPU.
- Real-world use case 02
Planning a production rollout
An engineer needs to know how many concurrent users they can support on a specific A100 cluster.
- Real-world use case 03
Comparing quantization trade-offs
A researcher wants to see the VRAM difference between BF16 and INT8 for a specific model.
Complete set · 4capabilities
The complete GPU Inference Memory Calculator capability set.
These are the exact actions your AI can choose when you ask it to work with GPU Inference Memory Calculator.
01—04
4 capabilities in this set.
Part of 4 available through GPU Inference Memory Calculator.
- 01 Capability
Calculate max batch capacity
Determines the largest batch size that fits within a specific GPU's memory limit. Use this to find your peak concurrent capacity.
- 02 Capability
Estimate total vram
Calculates the total VRAM required to run a specific batch size. This helps you predict crashes before they happen.
- 03 Capability
Get kv cache per request
Calculates the memory footprint of the Key-Value cache for a single request. This accounts for context overhead.
- 04 Capability
Get model weights size
Calculates the amount of VRAM required just to load the model's parameters. It supports multiple precision types.
Set up in minutes
One URL. Then ask GPU Inference Memory Calculator to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use GPU Inference Memory Calculator from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_Po32HLoFfJyACkPs6caCBt7wRipx1gN5av2RafWO/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it GPU Inference Memory Calculator, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable GPU Inference Memory Calculator for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_Po32HLoFfJyACkPs6caCBt7wRipx1gN5av2RafWO/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the GPU Inference Memory Calculator URL.
- Step 03
Save and start
Save the connection and enable GPU Inference Memory Calculator in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"gpu-inference-memory-calculator": {
"url": "https://edge.vinkius.com/vk_preview_Po32HLoFfJyACkPs6caCBt7wRipx1gN5av2RafWO/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using GPU Inference Memory Calculator
Open Agent mode in chat and ask: "Using GPU Inference Memory Calculator, help me...". 4 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"gpu-inference-memory-calculator": {
"url": "https://edge.vinkius.com/vk_preview_Po32HLoFfJyACkPs6caCBt7wRipx1gN5av2RafWO/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using GPU Inference Memory Calculator
Ask Copilot: "Using GPU Inference Memory Calculator, help me...". 4 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"gpu-inference-memory-calculator": {
"url": "https://edge.vinkius.com/vk_preview_Po32HLoFfJyACkPs6caCBt7wRipx1gN5av2RafWO/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using GPU Inference Memory Calculator
Open Cascade and ask: "Using GPU Inference Memory Calculator, help me...". 4 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"gpu-inference-memory-calculator": {
"url": "https://edge.vinkius.com/vk_preview_Po32HLoFfJyACkPs6caCBt7wRipx1gN5av2RafWO/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using GPU Inference Memory Calculator
Ask Cline: "Using GPU Inference Memory Calculator, help me...". 4 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add gpu-inference-memory-calculator --transport http "https://edge.vinkius.com/vk_preview_Po32HLoFfJyACkPs6caCBt7wRipx1gN5av2RafWO/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using GPU Inference Memory Calculator
Ask Claude: "Using GPU Inference Memory Calculator, show me...". 4 tools are ready
Where the request belongs
Work GPU Inference Memory Calculator can move forward.
This is for ML engineers and infrastructure leads who need to plan hardware for LLM deployment. It's for the person who needs to know if a 70B model will actually fit on their existing cluster without crashing.
MLOps Engineer
Planning production inference scaling and choosing the right GPU instances for a fleet.
AI Researcher
Testing different quantization levels to see how they affect memory and speed on local hardware.
Hardware Architect
Mapping out the hardware budget for a new company-wide LLM project and estimating costs.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsCerebras Inference
Access lightning-fast AI inference via Cerebras Wafer-Scale Engine. generate chat completions, manage models, and run batch jobs at record speeds.
NVIDIA AI
Access LLMs, embeddings, code generation, and reasoning via NVIDIA API Catalog.
Vast.ai (GPU Rental Cloud API)
Rent high-performance GPUs for AI and deep learning. Search marketplace offers, deploy Docker containers, and manage your cloud GPU fleet.
NVIDIA API Catalog
Cloud Engine proxy running native foundational completions natively utilizing active Nemotron and Llama3 architectures.
Groq
Run large language models at unprecedented speed with custom LPU hardware that delivers real-time AI inference at massive scale.
CoreWeave (AI GPU Cloud)
Manage high-performance AI infrastructure on CoreWeave. provision GPU clusters, configure VPCs, and orchestrate inference gateways directly from your AI agent.
Bring your own AI
Change the model, client or framework. Keep GPU Inference Memory Calculator connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about GPU Inference Memory Calculator.
The practical details behind the request, access and result.
Can the GPU Inference Memory Calculator help me choose the right GPU?
Yes, it shows you the exact VRAM needs for different models and precisions so you can pick the right hardware for your needs.
Does this capability actually run the LLM for me?
No, it only calculates the memory requirements. You'll still need a separate inference engine to run the model.
How does the GPU Inference Memory Calculator handle different precisions?
You can specify types like FP32, FP16, BF16, INT8, or INT4 to see how much memory each one saves for your specific model.
Can I use this to see how many users I can support?
You can use it to find the max batch capacity, which tells you how many concurrent requests your hardware can handle at once.
Is this useful for production planning?
It's perfect for production because it helps you avoid out-of-memory crashes by predicting the total VRAM needed for your specific batch size.
What's the difference between weight size and KV cache?
The weight size is just for loading the model, while the KV cache is the extra memory needed for the actual conversation context.
What precision modes are supported?
The calculator supports FP32, FP16, BF16, INT8, and INT4 precision modes.
How do I calculate the total VRAM for a batch?
You can use the estimate_total_vram capability by providing the pre-calculated weight memory, KV cache size per request, and your desired batch size.
Can I determine the maximum number of concurrent requests for my GPU?
Yes, use calculate_max_batch_capacity by providing your total VRAM budget, model weight memory, and KV cache size per request.
One connection away
Give your agent a direct line to GPU Inference Memory Calculator.
Connect GPU Inference Memory Calculator once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available