# Nodegrove VRAM: can I run it?

> Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.

- name: io.nodegrove/vram-mcp
- version: 1.1.4
- connection class: R0 (autonomous)
- trust: 99/100
- quality: 100/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.nodegrove%2Fvram-mcp
- tools: https://api.protogrid.dev/v1/servers/io.nodegrove%2Fvram-mcp/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "vram-mcp": {
      "type": "http",
      "url": "https://mcp.nodegrove.io/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 98
- freshness: 100
- provenance: 100
- drivers: +repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-95% +updated-1d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 100/100 (strong)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 3600000)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 2,723 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 3 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: dependencies not resolved yet

- tools: 6, about 2,723 tokens to load them all
- tool set hash: 16e76380f6438aacc8e9ea2499385d64
- tools last changed: 2026-10-16T02:39:08.706Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.nodegrove/vram-mcp.svg)](https://protogrid.dev/servers/io.nodegrove/vram-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-16 `list_models` changed (description)
  - before: The open-weight LLMs nodegrove.io has verified against their config.json (data version 2026-10-09): id, size, attention design, native context, licence, memory at Q4 with 8k context and each model's page.
  - after: The open-weight LLMs nodegrove.io has verified against their config.json (data version 2026-10-16): id, size, attention design, native context, licence, memory at Q4 with 8k context and each model's page.
- 2026-10-09 `list_models` changed (description)
  - before: The open-weight LLMs nodegrove.io has verified against their config.json (data version 2026-10-06): id, size, attention design, native context, licence, memory at Q4 with 8k context and each model's page.
  - after: The open-weight LLMs nodegrove.io has verified against their config.json (data version 2026-10-09): id, size, attention design, native context, licence, memory at Q4 with 8k context and each model's page.
- 2026-10-05 `list_models` changed (description)
  - before: The open-weight LLMs nodegrove.io has verified against their config.json (data version 2026-09-25): id, size, attention design, native context, licence, memory at Q4 with 8k context and each model's page.
  - after: The open-weight LLMs nodegrove.io has verified against their config.json (data version 2026-10-06): id, size, attention design, native context, licence, memory at Q4 with 8k context and each model's page.

Full history: https://api.protogrid.dev/v1/servers/io.nodegrove%2Fvram-mcp/changes

## Dependencies

- npm @nodegrove/vram-mcp@1.1.4: pending

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://mcp.nodegrove.io/mcp (streamable-http, auth none, reachable true, uptime30d 0.95384616)

## Packages

- npm @nodegrove/vram-mcp@1.1.4

## Tools (6)

- `can_i_run`: Can this GPU run this open-weight LLM? Returns fits, tight or no, the memory split (weights, KV cache, overhead), a decode-speed ceiling, the longest context that fits and, on a no, every change that would make it fit: quantisation, KV cache, context, another card or a smaller model. Model: a name or id from list_models, any Hugging Face repo id, or its architecture. GPU: a name or id from list_gpus, or vram_gb for any other card.
- `estimate_from_hf_repo`: Reads any Hugging Face model repo's config.json and parameter count and estimates its memory: the attention layout found (standard, sliding-window, hybrid or latent), how much each 1,000 tokens of context costs, and weights + KV cache + overhead at every quantisation. For models nodegrove.io has not reviewed; anything the reader cannot model is listed in warnings.
- `estimate_vram`: How much memory an LLM needs: weights + KV cache + overhead at each quantisation (or one), at a given context, and the smallest common card class that holds each. Model: a name or id from list_models, any Hugging Face repo id, or its architecture (params_b, layers, kv_heads, head_dim).
- `list_gpus`: The GPUs and machines nodegrove.io covers: memory, the memory a runtime can use and bandwidth, from the makers' specs, with each one's page.
- `list_models`: The open-weight LLMs nodegrove.io has verified against their config.json (data version 2026-10-16): id, size, attention design, native context, licence, memory at Q4 with 8k context and each model's page.
- `what_fits`: Which open-weight LLMs fit this GPU: every model in list_models checked at one quantisation and context, with a recommended everyday model (the biggest class that fits with room for context at conversational speed), the largest that fits, the best at Q8 and the first out of reach. GPU: a name or id from list_gpus, or vram_gb for any other card.