modelread
v0.3.1Will this Hugging Face model run on my hardware? Fit, best quant, tok/s range, launch command.
Endpoint health
online- Last checked
- 11/20/2026, 6:17:08 AM
- Latency
- 63 ms
- Consecutive failures
- 0
- Endpoint reachable: pass
- Protocol valid: pass
- MCP handshake valid: pass
Machine-readable profile
mcp-server · schema v1 · callable
mcp-server:com.modelread%2Fmodelread
Connect this server
Generated config contains no credentials. Keep any required secrets in your client's local environment.
{
"mcpServers": {
"com.modelread/modelread": {
"url": "https://modelread.com/mcp"
}
}
}Indexed tools
Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.
11 shown · authentication unknown
Ask about running models
ask
Free-form question about running Hugging Face models locally or self-hosted (runtimes, quant choice, KV cache, why something OOMs, MoE offload); returns markdown plus the parsed query and notes.
Schema valid · SHA-256 935d8607b608…
View input schema
{ "type": "object", "properties": { "question": { "title": "Question", "type": "string" } }, "required": [ "question" ], "title": "askArguments" }Compare one model across devices
compare_hardware
Run one repo against several devices and return the best candidate per device (verdict, quant, decode band, max context, launch command), sorted best first. Use for 'which of my machines should run X' or 'is a 4090 or an M4 Max better for X'. hardware: comma-separated list of presets / free text (max 8).
Schema valid · SHA-256 52b226c9ced0…
View input schema
{ "type": "object", "properties": { "repo": { "title": "Repo", "type": "string" }, "hardware": { "title": "Hardware", "type": "string" }, "ctx": { "default": 8192, "title": "Ctx", "type": "integer" } }, "required": [ "repo", "hardware" ], "title": "compare_hardwareArguments" }Estimate model fit and speed
estimate_fit
Connections
streamable-http
https://modelread.com/mcp
streamable-http
https://patrickbdevaney-modelread-mcp.hf.space/gradio_api/mcp/