{"name":"io.github.hongping-zh/ecocompute-estimator","slug":"hongping-zh-ecocompute-estimator","title":"EcoCompute Should-I-Quantize Estimator","description":"Energy impact of LLM quantization, calibrated to measured GPU data. Every answer states its basis.","url":"https://mcp.market/server/hongping-zh-ecocompute-estimator","rating":null,"grade":"A","score":91,"certified":false,"status":"active","category":"ai","tags":["ai"],"presence":{"score":23,"stars":0,"forks":0,"downloads_week":null,"last_push_at":"2026-10-24T03:30:47.000Z","license":null},"uptime":{"percent":100,"checks":28,"ok":28,"last_checked_at":"2026-11-04T07:25:32.344Z","last_ok_at":"2026-11-04T07:25:32.344Z","latency_ms":259},"claimed":false,"transport":"remote","callable_via_gateway":true,"default_price_micros":0,"repository":"https://github.com/hongping-zh/quant-energy","website":"https://quantenergy.tech","version":"1.0.0","remotes":[{"type":"streamable-http","url":"https://ecocompute-estimator.zhanghongping1982.workers.dev/mcp"}],"packages":[],"tools":[{"name":"estimate_quantization_energy","description":"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.","write_action":false,"price_micros":0,"input_schema":{"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'"}}}},{"name":"get_quantization_crossover","description":"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.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"arch":{"type":"string","enum":["turing","ada","blackwell","ampere","hopper"],"description":"optional: limit to one architecture"}}}},{"name":"list_data_coverage","description":"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.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{}}},{"name":"search_measurements","description":"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.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"query":{"type":"string","description":"model ('TinyLlama'), GPU ('4090'), architecture ('ampere') or size ('7')"}},"required":["query"]}}],"scan":{"score":91,"grade":"A","scanned_at":"2026-10-24T04:04:06.061Z","report":{"scannerVersion":"0.1.10","scannedAt":"2026-10-24T04:04:05.995Z","components":{"code":{"score":-1,"max":25,"notes":["remote-only server, no package to scan"]},"reliability":{"score":20,"max":20,"notes":["remote reachable in 221ms"]},"poisoning":{"score":15,"max":15,"notes":["4 tool descriptions checked"]},"auth":{"score":10,"max":15,"notes":["open endpoint, read-only tools"]},"maintenance":{"score":15,"max":15,"notes":["last push 0 days ago"]},"identity":{"score":8,"max":10,"notes":["registry namespace matches repository owner","GitHub account older than a year"]}},"findings":[],"inputs":{"probes":[{"url":"https://ecocompute-estimator.zhanghongping1982.workers.dev/mcp","reachable":true,"authRequired":false,"latencyMs":221,"serverInfo":{"name":"ecocompute-estimator","version":"1.1.0"}}],"packages":[],"repo":{"found":true,"owner":"hongping-zh","repo":"quant-energy","archived":false,"pushedAt":"2026-10-24T03:30:47Z","stars":0,"forks":0,"openIssues":0,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/133202211?v=4","ownerCreatedAt":"2023-05-11T07:28:19Z"},"icon":{"url":null,"source":"none"},"presence":{"stars":0,"forks":0,"downloadsWeek":null,"license":null,"lastPushAt":"2026-10-24T03:30:47.000Z","score":23}}}},"grade_history":[],"reviews":[]}