Skip to main content
Glama

FitLLM

by run.fitllm
OverviewAdmin

Check if an LLM fits on hardware

check_llm_fit
Read-onlyIdempotent

Check whether a specific local LLM fits in the memory of a specific GPU or Apple Silicon Mac. Returns fits/tight/won't-fit verdict with the memory breakdown (weights, KV cache, linear-attention state when present, runtime overhead, reserve), max context, and a concrete fix if it doesn't fit. Use this whenever a user asks anything like "can I run on my <GPU/Mac>?", "will fit in GB?", or "what do I need to run ?". Estimates using curated, config-derived architecture fields (MLA, sliding-window, hybrid attention, MoE modeled).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ctxNoAlias of context_tokens — accepted because the REST API uses this name. Do not pass both with different values.
gpuNoGPU name, fuzzy — e.g. "RTX 4090", "RX 7900 XTX", "A100 80GB". Multi-GPU rigs: join with + — e.g. "RTX 5090 + RTX 3090" (VRAM pools across cards). Provide gpu OR mac_ram_gb.
modelYesLLM name, fuzzy — e.g. "GLM-4.7-Flash", "gpt-oss-20b", "gemma 31b"
quantNoWeight quantization. GPU: Q4_K_M(default)/Q5_K_M/Q6_K/Q8_0/FP16. Mac: 4/8(default)/16 (bits).
kv_bitsNoKV-cache quantization bits (default 16 = F16)
gpu_countNoNumber of identical copies of the gpu (e.g. gpu="RTX 3090", gpu_count=2 for a 2×3090 rig). Default 1.
mac_ram_gbNoApple Silicon unified memory in GB — e.g. 16, 64, 512. Provide gpu OR mac_ram_gb.
context_tokensNoContext length in tokens (default 8192). Alias: ctx (same field as the REST API).

Schema Changelog

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

  1. Changed2 schema fields changed
    • changedInput schema / properties / context_tokens / description
      Previous value: -"Context length in tokens (default 8192)"New value: +"Context length in tokens (default 8192). Alias: ctx (same field as the REST API)."
    • addedInput schema / properties / ctx
      Added value: +{
+  "description": "Alias of context_tokens — accepted because the REST API uses this name. Do not pass both with different values.",
+  "minimum": 1024,
+  "type": "integer"
+}
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description adds meaningful behavioral detail beyond that safety profile: the exact return structure (verdict, memory breakdown, max context, concrete fix) and the estimation methodology with modeled architecture types (MLA, sliding-window, hybrid attention, MoE). The phrase 'Estimates using curated...' transparently signals approximation. No contradiction with annotations.

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?

Four purposeful sentences: scope and purpose, return value, usage triggers, and methodology/limitations. Every sentence earns its place, the main action is front-loaded, and there is no redundancy or filler.

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 is largely self-contained: it covers when to use the tool, what it returns, and key modeling assumptions. Because there is no output schema, the explicit listing of returned fields is valuable. It could be slightly more complete by naming sibling alternatives or addressing edge-case behavior, but the schema and description together provide a solid invocation contract.

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%, and the input schema already documents every parameter with defaults, units, aliases, and mutual-exclusion constraints (gpu OR mac_ram_gb). The description adds only high-level framing ('specific local LLM', 'GPU or Apple Silicon Mac') and does not need to compensate for missing parameter documentation. Baseline 3 is appropriate.

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 opens with a specific verb ('Check') and precisely scopes the operation to a specific local LLM against a specific GPU or Apple Silicon Mac, thereby distinguishing it from the broader sibling tools list_supported and what_fits_on_hardware. It also names the concrete verdict categories (fits/tight/won't-fit), leaving no ambiguity about what the tool does.

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

Usage Guidelines4/5

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

The description explicitly provides trigger phrases ('can I run...', 'will...fit in...', 'what do I need to run...') and instructs 'Use this whenever', giving the agent clear, actionable context for when to invoke the tool. It does not explicitly name sibling alternatives or state when those tools should be used instead, so it stops short of full when/when-not guidance.

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

All FitLLM toolsInspect
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.

Resources