Will a local LLM run on your hardware? GGUF quant, buy-vs-rent-vs-API cost, used-GPU prices.
Déduit des transports déclarés par cette annonce (streamable-http). Un client absent de cette liste n’est pas écarté pour autant — c’est simplement quelque chose que Forge ne peut pas confirmer.
La vérification confirme l’identité de l’éditeur (la propriété du dépôt), pas la sûreté du code. L’analyse de sécurité couvre les CVE connues et les scripts d’installation suspects.
Lu depuis un véritable échange MCP initialize → tools/list contre l’endpoint déclaré. Aucun outil n’a été invoqué — tools/list est l’appel d’introspection en lecture seule que le protocole prévoit pour cela. Cela reflète ce que le serveur annonçait à cet instant ; un endpoint hébergé n’est figé sur aucune version et peut changer sans préavis.
https://vettedconsumer.com/mcp9 outils · 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.
| Paramètre | Type | Description |
|---|---|---|
| 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.
| Paramètre | Type | Description |
|---|---|---|
| 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.
| Paramètre | Type | Description |
|---|---|---|
| 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).
Aucun schéma d’entrée n’a été publié pour cet outil.
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).
Aucun schéma d’entrée n’a été publié pour cet outil.
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/.
| Paramètre | Type | Description |
|---|---|---|
| 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.
| Paramètre | Type | Description |
|---|---|---|
| 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).
| Paramètre | Type | Description |
|---|---|---|
| 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.
| Paramètre | Type | Description |
|---|---|---|
| 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 outils sur 9 ont publié une description.
Les noms et descriptions d’outils sont écrits par l’éditeur et affichés tels quels, comme du texte inerte. Ce sont les chaînes qu’un client MCP transmet à un modèle, alors Forge y recherche des motifs d’injection de prompt — tout constat apparaît avec l’analyse de sécurité ci-dessus. « Privilégié » est une correspondance de mot-clé sur le nom de l’outil, pas un audit de ce qu’il fait : un nom anodin peut tout de même tout faire.
Will a local LLM run on your hardware? GGUF quant, buy-vs-rent-vs-API cost, used-GPU prices.
Les noms cliquables ouvrent l’index Forge de toutes les entrées observées exposant cet outil. Parcourir tous les outils indexés.
Cette entrée ne publie aucun paquet npm : Forge n'a donc pas d'arbre de dépendances pour elle. C'est une lacune de couverture — pas une affirmation qu'elle n'a aucune dépendance.