vetted-consumer

Recommend a quant

recommend_quant

Which GGUF quantization to download for a model on given hardware: the full quant ladder with file size, max context, and tok/s for each, plus the recommended pick.

Input Schema

TableJSON Schema

Name	Required	Description
`model`	No	Model name, e.g. 'Llama 70B', 'gpt-oss-120B', 'Qwen 32B'. Use list_models to see known names.
`mxfp4`	No	True if the model ships natively in MXFP4 (e.g. gpt-oss)
`context`	No	Context window in tokens (default 8192)
`total_b`	No	For an unlisted model: total parameters in billions
`unified`	No	True for unified-memory machines (Macs, Strix Halo, CPU+RAM)
`vram_gb`	No	For custom hardware: VRAM or unified memory in GB
`active_b`	No	For an unlisted model: active params in billions (= total for dense, less for MoE)
`hardware`	No	Hardware name/id, e.g. 'rtx-3090', 'Mac 128GB', 'Strix Halo'. Use list_hardware to see known ones.
`kv_precision`	No	KV cache precision (default f16)
`bandwidth_gbps`	No	For custom hardware: memory bandwidth in GB/s

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedJun 23, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description bears full burden. It discloses the output (full ladder with file size, max context, tok/s, recommended pick). However, it does not mention any side effects, authentication, or rate limits, which are less critical for a recommendation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that efficiently conveys purpose and output without extraneous words. Every part earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains the output clearly (full quant ladder with file size, max context, tok/s, recommended pick), compensating for the lack of an output schema. However, it does not cover error handling or what happens if hardware/model is not found, leaving minor gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add any additional meaning beyond what the schema provides for parameters, leaving all semantic weight to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: to recommend a GGUF quantization for a model on given hardware, providing a ladder with file size, max context, tok/s, and a pick. This distinguishes it from sibling tools like 'can_i_run_it' or 'recommend_hardware'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when needing quantization recommendations but does not explicitly state when to use this tool versus alternatives or when not to use it. No exclusions or context for sibling differentiation is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All vetted-consumer tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0

Disambiguation4/5

Tools have mostly distinct purposes, though there is some overlap between cheapest_hardware_for_model and recommend_hardware, which both suggest machines for a model. Can_i_run_it also partially overlaps with these. However, descriptions clearly differentiate them.

Naming Consistency3/5

Most tools follow verb_noun pattern (list_hardware, compare_hardware), but can_i_run_it is a question and cost_compare is noun_verb, creating minor inconsistency.

Tool Count5/5

9 tools is well-scoped for a domain of hardware/model comparison, covering all key actions without being excessive.

Completeness4/5

Covers main workflows: compatibility check, cost analysis, recommendations, and listings. Lacks advanced filtering or detailed hardware specs, but core functionality is present.

Resources

Need Help?