The first Task-Aware MCP server and automated VRAM calculator for LLM fine-tuning. Instantly snipe the cheapest, fastest GPUs across 10+ cloud providers.
-
Updated
May 8, 2026 - Python
#
vram-calculator
Here are 11 public repositories matching this topic...
Accurate LLM memory/VRAM calculator — models sliding-window/linear/MoE attention & heterogeneous head_dim where naive calculators are 4–11× off. Apple Silicon + NVIDIA RTX · GGUF · F16/Q8/Q4 KV-cache quant · one MIT file. Powers fitllm.run.
inference nvidia moe quantization gemma mlx vram kv-cache apple-silicon llm llama-cpp local-llm ollama qwen gguf localllama memory-calculator vram-calculator
-
Updated
Jun 4, 2026 - JavaScript
🚀 A lightweight CLI to estimate hardware requirements and quantization compatibility for Hugging Face models.
-
Updated
Jan 25, 2026 - Python
A collection of serverless, blazing-fast web tools: Docker Compose Generator, LLM VRAM Calculator, NAS RAID Capacity, and Nginx Reverse Proxy Builder.
selfhosted homelab docker-compose-generator pseo llm-tools satisfactory-calculator raid-calculator vram-calculator zfs-calculator reverse-proxy-generator off-grid-solar nginx-config-generator
-
Updated
May 24, 2026 - Astro
Anthropic-standard Skill — decide API-vs-self-host LLM costs and fine-tune ROI from any agent context (Claude Code, Cursor, Codex). Live GPU+API prices, deterministic local math.
self-hosting lora fine-tuning finetuning llm llm-cost agent-skills claude-code vram-calculator claude-skills claude-skill agent-skill codex-skill skill-md cursor-skills cursor-skill gpu-pricing llm-cost-calculator
-
Updated
May 28, 2026 - Python
A CLI tool for estimating GPU VRAM requirements for Hugging Face models, supporting various data types, parallelization strategies, and fine-tuning scenarios like LoRA.
gpu-memory vram huggingface pipeline-parallelism memory-estimation huggingface-models hugging-face-transformers huggingface-datasets vram-monitoring vram-calculator vram-memory-estimation
-
Updated
Oct 22, 2025 - Python
macOS menu bar tool to explore Hugging Face models, detect GGUF/Safetensors configs, and calculate precise VRAM footprint and KV cache overhead.
macos swift ai quantization macos-app swiftui menu-bar-app huggingface llm safetensors gguf vram-calculator
-
Updated
May 14, 2026 - Swift
A lightweight CLI tool to inspect ML checkpoints (.safetensors, .gguf, .pt) and calculate inference VRAM, multi-GPU memory splits, and vLLM serving capacity.
-
Updated
Jun 13, 2026 - Python
A simple CLI tool to fetch Hugging Face model metadata and estimate required VRAM/RAM for inference.
transformers inference python-cli huggingface memory-estimation resource-planning llm llm-deployment ai-infrastructure vram-calculator
-
Updated
Mar 14, 2026 - Python
🖥️ Check if any LLM fits your GPU. VRAM calculator with context-aware fitting, quantization support, and real-time performance estimates.
calculator machine-learning typescript ai gpu svelte hardware-acceleration sveltejs huggingface sveltekit ai-tools llm vram-calculator
-
Updated
Apr 28, 2026 - Svelte
Optimal GPU, VRAM, and RAM configurations for running DeepSeek R1 locally (7B to 671B models).
-
Updated
Feb 18, 2026
Improve this page
Add a description, image, and links to the vram-calculator topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the vram-calculator topic, visit your repo's landing page and select "manage topics."