EcoCompute Should-I-Quantize Estimator
Energy impact of LLM quantization, calibrated to measured GPU data. Every answer states its basis.
MCP-Server · von hongping-zh
Überblick
EcoCompute Should-I-Quantize Estimator ist ein MCP-Server von hongping-zh. Marktplätze, die wir lesen und die es listen: 1 (Official MCP Registry). Wir haben es erstmals am 2026-10-24 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-11-15.
Was es abfragt
- Läuft entfernt
Keiner der Marktplätze, die wir lesen, veröffentlicht seine Tools oder die abgefragten Einstellungen.
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Ein Ein-Klick-Link öffnet den Client, der vor dem Hinzufügen des Servers um Bestätigung bittet.
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als entfernter MCP-Server
Erstellt aus den Angaben von Official MCP Registry.
claude mcp add --transport http ecocompute-estimator https://ecocompute-estimator.zhanghongping1982.workers.dev/mcp
[mcp_servers.ecocompute-estimator]
url = "https://ecocompute-estimator.zhanghongping1982.workers.dev/mcp"
{
"mcpServers": {
"ecocompute-estimator": {
"url": "https://ecocompute-estimator.zhanghongping1982.workers.dev/mcp"
}
}
}
Wo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Official MCP Registry (Eintrag in der Registry öffnen) | Gelistet | 1.0.0 | Forks (GitHub): 0 Sterne (GitHub): 0 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
Was sich geändert hat
- Wird seitdem als Produkt geführt
- Official MCP Registry: erschienen
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
Intelligent CLI tool with AI-powered model selection that analyzes your hardware and recommends optimal LLM models for your system
-
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
-
optimization
Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.
-
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
-
Does an LLM fit on your GPU? VRAM, KV cache and GPU count for any Hugging Face model.
-
wattindex io.github.CloudCorpRecords/wattindex
GPU energy per million output tokens by model and GPU, with grid carbon intensity.
-
ai-economics pl.piszczek/ai-economics
12 calculators for AI cost, energy and agent verification. Free API, no key.
-
Cheapest API for any model across official, inference and relay providers; find free credits
-
Quantization workflows and troubleshooting for vLLM-Omni.
-
Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
Autonomous experiment loop for Claude Code. Run an endless optimize-measure-keep/discard cycle on any optimization target: LLM training loss, test speed, bundle size, build time…
-
Context engineering plugin for Claude Code — real-time prompt scoring, RLM adaptive weights, and token optimization. Scores every tool use across 5 dimensions (token utilization…
-
Synthetic monitoring for LLM inference endpoints. Probe TTFT, latency, throughput, and errors across OpenAI, Anthropic, Google, Azure, Bedrock, and any OpenAI-compatible server.
Gelistet auf Claude Code: claude-plugins-official (5)
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom…
-
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
-
Build, train, evaluate, and use open source AI models, datasets, and spaces.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
Gelistet auf Claude: knowledge-work-plugins (5)
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Agent skills for Qdrant vector search covering scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Predict structures, screen molecules and proteins, and design binders.
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
Gelistet auf Community GitHub marketplaces (5)
-
optimization
Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.
-
Quantization workflows and troubleshooting for vLLM-Omni.
-
vllm
Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment, quantization-aware model configuration (tensor parallelism, KV cache…
-
llama-cpp
Operate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or multi-GPU systems. Use when installing or building…
-
Qualcomm AI Hub Models authoring skills (onboard, validate-on-device, add-quantization)
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Multi-model council for Copilot CLI: three subagents on different model families (Anthropic, OpenAI, Google) answer independently, then build on each other or attack the leading…
-
Visualizes live session AI-credit usage as a Pac-Man board with pellets, ghosts, fruit milestones, and game-over limits.
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
-
See your local Copilot token usage by day, model, and session, and get tips to use it more efficiently.
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
Gelistet auf Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Ask Databricks Genie questions about your workspace's data in plain language.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Explore datasets and tables and run SQL queries.
Gelistet auf Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Seamless interaction with Novita AI platform resources.
-
Tools for interacting with Hugging Face models, datasets, research papers, and more.
-
Connect your chat repl to wolfram alpha computational intelligence.
Gelistet auf Official MCP Registry (5)
-
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
-
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
-
Does an LLM fit on your GPU? VRAM, KV cache and GPU count for any Hugging Face model.
-
wattindex io.github.CloudCorpRecords/wattindex
GPU energy per million output tokens by model and GPU, with grid carbon intensity.
-
ai-economics pl.piszczek/ai-economics
12 calculators for AI cost, energy and agent verification. Free API, no key.
Gelistet auf PyPI (MCP servers) (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
offline-mcp io.github.gabrielmahia/offline-mcp
Local AI over Ollama for low connectivity: status, local inference, model and deployment guides.
-
Read, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline.
-
mcp-memory-service-lite
Lightweight semantic memory service with ONNX embeddings - no PyTorch required. 80% smaller install size. REST API + MCP transport.
-
local-delegate io.github.ZahiriNatZuke/local-delegate
Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.
Gelistet auf npm registry (MCP servers) (5)
-
Intelligent CLI tool with AI-powered model selection that analyzes your hardware and recommends optimal LLM models for your system
-
Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
-
Alibaba Cloud DashScope — Qwen
Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.
-
Tells your agent which model to use and what it costs, across 46 providers and local runtimes.
-
qwen-2-mcp io.github.runapi-builder/qwen-2-mcp
RunAPI MCP server for Qwen 2: create tasks, poll status, check pricing.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Möchten Sie dieses Zeichen für Ihr Plugin in unserem Katalog?
Belegen Sie mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag, dass Sie es pflegen, und Sie können dieses Zeichen auf der Karte zeigen, dazu Live-Banner für Ihre Website und Ihr README. So funktioniert die Verifizierung
Außerdem erhalten Sie Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Official MCP Registry. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.