Will a local LLM run on your hardware? GGUF quant, buy-vs-rent-vs-API cost, used-GPU prices.
Dedotto dai trasporti dichiarati da questo annuncio (streamable-http). Un client che non compare qui non è escluso — semplicemente Forge non è in grado di confermarlo.
La verifica conferma l’identità del publisher (la proprietà del repo), non la sicurezza del codice. L’analisi di sicurezza copre i CVE noti e gli script di installazione sospetti.
Letto da un vero handshake MCP initialize → tools/list verso l’endpoint dichiarato. Nessuno strumento è stato invocato — tools/list è la chiamata di introspezione in sola lettura che il protocollo prevede a questo scopo. Riflette ciò che il server annunciava in quel momento; un endpoint ospitato non è vincolato ad alcuna versione e può cambiare senza preavviso.
https://vettedconsumer.com/mcp9 strumenti · 184 mscan_i_run_itWill a given local LLM run on given hardware? Returns fit, the best quant that fits, theoretical tok/s, and real owner-measured tok/s where available.Will a given local LLM run on given hardware? Returns fit, the best quant that fits, theoretical tok/s, and real owner-measured tok/s where available.
| Parametro | Tipo | Descrizione |
|---|---|---|
| model | string | Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names. |
| total_b | number | For an unlisted model: total parameters in billions |
| active_b | number | For an unlisted model: active params in billions (= total for dense, less for MoE) |
| mxfp4 | boolean | True if the model ships natively in MXFP4 (e.g. gpt-oss) |
| hardware | string | Hardware name/id, e.g. 'rtx-3090', 'Mac 128GB', 'Strix Halo'. Use list_hardware to see known ones. |
| vram_gb | number | For custom hardware: VRAM or unified memory in GB |
| bandwidth_gbps | number | For custom hardware: memory bandwidth in GB/s |
| unified | boolean | True for unified-memory machines (Macs, Strix Halo, CPU+RAM) |
| context | number | Context window in tokens (default 8192) |
| kv_precision | string | KV cache precision (default f16) |
recommend_quantWhich GGUF quantization to download for a model on given hardware: the full quant ladder with file size, max context, and tok/s for each, plus the recommended pick.Which GGUF quantization to download for a model on given hardware: the full quant ladder with file size, max context, and tok/s for each, plus the recommended pick.
| Parametro | Tipo | Descrizione |
|---|---|---|
| model | string | Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names. |
| total_b | number | For an unlisted model: total parameters in billions |
| active_b | number | For an unlisted model: active params in billions (= total for dense, less for MoE) |
| mxfp4 | boolean | True if the model ships natively in MXFP4 (e.g. gpt-oss) |
| hardware | string | Hardware name/id, e.g. 'rtx-3090', 'Mac 128GB', 'Strix Halo'. Use list_hardware to see known ones. |
| vram_gb | number | For custom hardware: VRAM or unified memory in GB |
| bandwidth_gbps | number | For custom hardware: memory bandwidth in GB/s |
| unified | boolean | True for unified-memory machines (Macs, Strix Halo, CPU+RAM) |
| context | number | Context window in tokens (default 8192) |
| kv_precision | string | KV cache precision (default f16) |
cheapest_hardware_for_modelThe cheapest catalogued, buyable machine that runs a given model at Q4 with the requested context.The cheapest catalogued, buyable machine that runs a given model at Q4 with the requested context.
| Parametro | Tipo | Descrizione |
|---|---|---|
| model | string | Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names. |
| total_b | number | For an unlisted model: total parameters in billions |
| active_b | number | For an unlisted model: active params in billions (= total for dense, less for MoE) |
| mxfp4 | boolean | True if the model ships natively in MXFP4 (e.g. gpt-oss) |
| context | number | Context window in tokens (default 8192) |
list_modelsList the local LLM model classes the tools know about (params, dense/MoE, native context).List the local LLM model classes the tools know about (params, dense/MoE, native context).
Per questo strumento non è stato pubblicato alcuno schema di input.
list_hardwareList the machines the tools know about (memory, bandwidth, price, buy link).List the machines the tools know about (memory, bandwidth, price, buy link).
Per questo strumento non è stato pubblicato alcuno schema di input.
cost_compareBuy vs rent vs API cost to run a model locally: monthly/1y/3y totals, break-even months, and the energy cost per 1M tokens. Same math as /cost-calculator/.Buy vs rent vs API cost to run a model locally: monthly/1y/3y totals, break-even months, and the energy cost per 1M tokens. Same math as /cost-calculator/.
| Parametro | Tipo | Descrizione |
|---|---|---|
| hardware | string | Catalogued hardware name/id (see list_hardware), e.g. 'rtx-3090-used' |
| price_usd | number | For custom hardware: price in USD |
| tdp_w | number | For custom hardware: board power draw in watts |
| hours | number | Active hours per day (default 3) |
| tokens | number | Tokens generated per day, for the API comparison (default 300000) |
| kwh | number | Electricity $/kWh (default 0.16) |
| rent | number | Cloud GPU $/hour (default 0.59) |
| api | number | API $/million tokens (default 1.0) |
recommend_hardwareRanked list of catalogued, buyable machines that run a model at the requested context, cheapest first, with an optional budget cap.Ranked list of catalogued, buyable machines that run a model at the requested context, cheapest first, with an optional budget cap.
| Parametro | Tipo | Descrizione |
|---|---|---|
| model | string | Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names. |
| total_b | number | For an unlisted model: total parameters in billions |
| active_b | number | For an unlisted model: active params in billions (= total for dense, less for MoE) |
| mxfp4 | boolean | True if the model ships natively in MXFP4 (e.g. gpt-oss) |
| context | number | Context window in tokens (default 8192) |
| kv_precision | string | KV cache precision (default f16) |
| budget | number | Optional max price in USD |
get_used_gpu_pricesCurrent typical used-GPU prices for local-AI rigs (eBay Browse API median asking + hand-verified, monthly).Current typical used-GPU prices for local-AI rigs (eBay Browse API median asking + hand-verified, monthly).
| Parametro | Tipo | Descrizione |
|---|---|---|
| gpu | string | Optional name/id filter, e.g. "3090" |
compare_hardwareSide-by-side memory, bandwidth, price, and (with a model) fit + tok/s for 2 to 4 machines.Side-by-side memory, bandwidth, price, and (with a model) fit + tok/s for 2 to 4 machines.
| Parametro | Tipo | Descrizione |
|---|---|---|
| hardware* | string | 2 to 4 hardware names/ids, comma-separated |
| model | string | Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names. |
| total_b | number | For an unlisted model: total parameters in billions |
| active_b | number | For an unlisted model: active params in billions (= total for dense, less for MoE) |
| mxfp4 | boolean | True if the model ships natively in MXFP4 (e.g. gpt-oss) |
| context | number | Context window in tokens (default 8192) |
| kv_precision | string | KV cache precision (default f16) |
9 strumenti su 9 hanno pubblicato una descrizione.
I nomi e le descrizioni degli strumenti sono scritti dal publisher e mostrati alla lettera come testo inerte. Sono le stringhe che un client MCP passa a un modello, quindi Forge vi cerca schemi di prompt injection — ogni rilievo compare insieme all’analisi di sicurezza qui sopra. «Privilegiato» è una corrispondenza di parola chiave sul nome dello strumento, non una verifica di ciò che fa: un nome innocuo può comunque fare qualsiasi cosa.
Will a local LLM run on your hardware? GGUF quant, buy-vs-rent-vs-API cost, used-GPU prices.
I nomi collegati aprono l’indice Forge di tutte le voci osservate esporre quello strumento. Sfoglia tutti gli strumenti indicizzati.
Questa voce non pubblica alcun pacchetto npm, quindi Forge non ha un albero delle dipendenze per essa. È una lacuna di copertura, non l'affermazione che non abbia dipendenze.