Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Which tracked models run on a given GPU or Mac: measured GGUF weights + computed context cache + runtime overhead versus usable memory. Returns the best recommendation and every verdict (EXCELLENT/GOOD/TIGHT/OFFLOAD_REQUIRED/NOT_RECOMMENDED/UNKNOWN) with plain-language reasons. Get hardware ids from list_hardware.
Hardware id or page slug, e.g. rtx-4090, mac-studio-m3-ultra-96gb.
KV-cache quantization (default f16).
Restrict to one model slug.
Context length in tokens (default 8192).
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Which tracked models run on a given GPU or Mac: measured GGUF weights + computed context cache + runtime overhead versus usable memory. Returns the best recommendation and every verdict (EXCELLENT/GOOD/TIGHT/OFFLOAD_REQUIRED/NOT_RECOMMENDED/UNKNOWN) with plain-language reasons. Get hardware ids from list_hardware.
| Argument | Type | Description |
|---|---|---|
| kv | string | KV-cache quantization (default f16). |
| model | string | Restrict to one model slug. |
| context | integer | Context length in tokens (default 8192). |
| hardware* | string | Hardware id or page slug, e.g. rtx-4090, mac-studio-m3-ultra-96gb. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"hardware"
],
"properties": {
"kv": {
"enum": [
"f16",
"q8_0",
"q4_0"
],
"type": "string",
"description": "KV-cache quantization (default f16)."
},
"model": {
"type": "string",
"description": "Restrict to one model slug."
},
"context": {
"type": "integer",
"maximum": 1048576,
"minimum": 512,
"description": "Context length in tokens (default 8192)."
},
"hardware": {
"type": "string",
"description": "Hardware id or page slug, e.g. rtx-4090, mac-studio-m3-ultra-96gb."
}
}
}Median verified on-demand rental price per GPU class on Vast.ai (USD per hour), with min/p75 and offer counts, the collection timestamp, and per class the Rent Index: this week's median against last week and against the first week collected, a trend word, and the days excluded as marketplace glitches, plus RunPod's lowest posted on-demand price per class (a list price, not a median), Clore.ai's median for the same class (a second marketplace, never blended), and the AWS, Azure and Oracle Cloud pay-as-you-go list prices per GPU-hour, each with the instance type, VM size or bare-metal shape the price sits in (list prices, read four times a day, no statement about capacity). The index describes what prices did; it never forecasts.
No arguments.
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
}Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.
No arguments.
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
}Tracked AI models ranked by Heat Score (0–100, weighted percentiles of measured Hugging Face/OpenRouter signals) with the raw signals, local-run facts (GGUF size, quantization) and links. Models still collecting a week of history have heat=null and rank after scored ones.
| Argument | Type | Description |
|---|---|---|
| slug | string | Return a single model by slug. |
| limit | integer | How many models to return (default 12). |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"slug": {
"type": "string",
"description": "Return a single model by slug."
},
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1,
"description": "How many models to return (default 12)."
}
}
}The current pick of the week: one tracked model chosen by a published rule (largest counted Heat Score rise among models that run comfortably on a consumer card of up to 24 GB), with the numbers frozen at selection time, a device-by-device fit ladder and the written report including its caveats. Pass week (e.g. 2026-w37) for a past issue. issue is null until the first issue is published.
| Argument | Type | Description |
|---|---|---|
| week | string | ISO week label of a past issue, e.g. 2026-w37 (default: the current issue). |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"week": {
"type": "string",
"pattern": "^\\d{4}-w\\d{2}$",
"description": "ISO week label of a past issue, e.g. 2026-w37 (default: the current issue)."
}
}
}