io.nodegrove/vram-mcp
Nodegrove VRAM: can I run it?
io.nodegrove/vram-mcp costs 2 754 tokens of context per session. It has 6 tool definitions. That is 1.4 % of a 200k window. Measured 2026-10-03.
Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
alive probed 2026-10-03 · HTTP 200
6tools
2.8ktokens for the tool definitions
1.4 %of a 200k context window
2.0 sto initialize
54 msto list tools
- Endpoint
- https://mcp.nodegrove.io/mcp (streamable-http)
- Host
- mcp.nodegrove.io
- Protocol
- 2025-11-25
- Reports itself as
- nodegrove-vram 1.0.0
- Capabilities
- tools
- Instructions
- 570 characters
- Repository
- https://github.com/nodegrove/vram-mcp
- Website
- https://nodegrove.io/mcp
- Registry
- active, updated 2026-10-03 · registry entry
- Reachable
- 2 of the last 2 probes
Most expensive tools
| Tool | Tokens | Share of this server |
|---|---|---|
| can_i_run | 1 024 | 37 % |
| estimate_vram | 811 | 29 % |
| what_fits | 412 | 15 % |
| estimate_from_hf_repo | 288 | 10 % |
| list_models | 120 | 4 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Tokens |
|---|---|---|---|---|
| 2026-10-03 20:41 | alive | 2.0 s | 6 | 2.8k |
| 2026-10-03 17:56 | alive | 563 ms | 6 | 2.8k |
Badge
[](https://mcp-pulse.ulehla.dev/s/io.nodegrove/vram-mcp)