Skip to main content
Glama

Server Details

Will this Hugging Face model run on my hardware? Fit, best quant, tok/s range, launch command.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.8/5.0

Scored across 5 tools

Disambiguation4/5

The five tools split mostly cleanly between device listing, model search, recommendation, single-pair fit estimation, and multi-device comparison. The only real overlap is find_models vs search_models and estimate_fit vs compare_hardware; descriptions clarify the distinction, but an agent could still momentarily hesitate.

Naming Consistency5/5

All tools use the same modelread_mcp_ prefix followed by a verb_noun snake_case name (compare_hardware, estimate_fit, find_models, list_hardware, search_models). The pattern is fully consistent and predictable.

Tool Count5/5

Five tools are well-scoped for a model/hardware advisory service; each covers a distinct step: list hardware, search models, recommend models, estimate fit, and compare hardware. No tool feels redundant or missing from the count.

Completeness4/5

The set covers hardware discovery, model search/recommendation, single model-device fit, and multi-device comparison, which is the core workflow. Minor gaps exist: no dedicated get_model or get_hardware detail tool and no obvious way to enter arbitrary custom hardware outside presets, though agents can work around via search/list.

Available Tools

5 tools
modelread_mcp_compare_hardwareAInspect

Run one Hugging Face model against several devices and rank them (best first). Use for "which of my machines should run X" or "is a 4090 or an M4 Max better for X".

Inputs: ctx, repo, hardware_list.

modelread_mcp_estimate_fitAInspect

Will this Hugging Face model run on this hardware, how fast, with which quant, and with what command? Checks the repo and its quantized derivatives (GGUF / MLX / AWQ / FP8) from their real file sizes and tensor headers. Returns the best variant and alternatives, each with: verdict (fits | fits-tight | offload | no | unknown), decode and prefill tokens/sec as a calibrated range (lo/mid/hi with basis), longest context that fits, memory placement (VRAM / RAM / SSD) and an exact llama.cpp / vLLM / MLX launch command.

Inputs: ctx, repo, hardware, kv_cache_dtype.

modelread_mcp_find_modelsAInspect

Recommend open models for a task on a device, from a natural-language question. Ranks ~20k indexed Hugging Face models by fit, task benchmark percentile (vendor vs independent kept apart), quant quality and speed. Examples: "best coding model for an RTX 4090 + 64GB RAM at 32k context", "Japanese chat on a Galaxy S25 Ultra", "serve 8 users on 2x RTX 3090".

Inputs: question, default_hardware.

modelread_mcp_list_hardwareBInspect

List device presets: GPUs of every vendor, Apple Silicon, multi-GPU nodes, cloud instances (with $/hour), Jetson, phones, tablets, single-board computers and VPS tiers.

Inputs: limit, filter.

modelread_mcp_search_modelsAInspect

Search the modelread index of Hugging Face models by name and task (no fit estimate; fast).

Inputs: task, limit, query.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources