EcoCompute Should-I-Quantize Estimator
Energy impact of LLM quantization, calibrated to measured GPU data. Every answer states its basis.
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"ecocompute-estimator": {
"url": "https://ecocompute-estimator.zhanghongping1982.workers.dev/mcp"
}
}
}リモートエンドポイント
https://ecocompute-estimator.zhanghongping1982.workers.dev/mcpstreamable-httpできること
ツール一覧
ツール（4）
🟡estimate_quantization_energy(params_b, arch, precision, batch, ctx, ...)
Estimate the task-level energy change (ΔE% vs FP16) of weight-only quantization (NF4 or INT8) for a model of a given size on a GPU architecture class, from measured-anchored curves. The answer carries basis (measured/interpolated/estimated), confidence and evidence boundaries.
入力スキーマ
{
"type": "object",
"properties": {
"params_b": {
"type": "number",
"description": "model size in billions of parameters, e.g. 7"
},
"arch": {
"type": "string",
"enum": [
"turing",
"ada",
"blackwell",
"ampere",
"hopper"
],
"description": "GPU architecture class"
},
"precision": {
"type": "string",
"enum": [
"NF4",
"INT8"
],
"description": "quantization format (default NF4)"
},
"batch": {
"type": "integer",
"description": "batch size (default 1; >1 shrinks savings — modelled, not measured)"
},
"ctx": {
"type": "integer",
"description": "context length (default 2048)"
},
"q": {
"type": "string",
"description": "alternative: plain-English query, e.g. '13B on A100 int8 batch 32'"
}
}
}🟢get_quantization_crossover(arch)
Get the model-size crossover for NF4/INT8 per architecture: below it quantization costs energy, above it saves. Crossovers belong to a card + software stack, not an architecture — the answer says so.
入力スキーマ
{
"type": "object",
"properties": {
"arch": {
"type": "string",
"enum": [
"turing",
"ada",
"blackwell",
"ampere",
"hopper"
],
"description": "optional: limit to one architecture"
}
}
}🟢list_data_coverage
List what is actually measured (GPU architecture × precision × size range, NVML direct), what is borrowed/estimated, and where the gaps are. Use this before trusting an estimate at the edges of coverage, and to answer 'is there data for my GPU?' honestly.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢search_measurements(query)
Search the measured anchors by model name, GPU name, architecture or size. Returns ΔE% vs FP16 per anchor with run counts — the raw evidence behind the curves.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "model ('TinyLlama'), GPU ('4090'), architecture ('ampere') or size ('7')"
}
},
"required": [
"query"
]
}コミュニティ
エビデンス