Skip to main content
Glama

Server Details

Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.

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 2025-06-18
URL
ChatGPT
–
Claude
–

TDQS

A3.5/5.0

Scored across 3 tools

Disambiguation5/5

Each tool answers a distinct question: vram_fit evaluates a given config for a verdict, vram_max_rank searches for the largest fitting rank, and vram_probes returns raw measured data. The differing return shapes (verdict/margin vs. max rank vs. probe rows) make misselection unlikely.

Naming Consistency4/5

All three tools share a consistent 'vram_' prefix, which makes the set recognizable. The suffixes mix verb-like (fit) and noun-like (probes, max_rank) forms, a minor deviation from a strict pattern.

Tool Count4/5

Three tools is thin but well-matched to the narrow purpose of VRAM-fit estimation for LoRA training. Each tool earns its place with a distinct role.

Completeness4/5

The surface covers the core workflow: check a config, derive a max rank, and inspect raw probe data. A gap remains around discovering which GPUs/cards are available and other config axes, but agents can largely work around it.

Available Tools

3 tools
vram_fitA
Read-only
Inspect

Will this LoRA config train on a card with vram_gb GB? Returns verdict fits / tight / does_not_fit, the predicted peak in MB, the margin, how each part was derived, and any measured probe with the same settings.

Inputs: rank (required), vram_gb (required), os, dora, +6 more.

vram_max_rankB
Read-only
Inspect

Largest LoRA rank (multiple of 8) that fits with margin on a card with vram_gb GB, and the largest that is tight (a real run may fit, the one-step probe would not).

Inputs: vram_gb (required), dora, model, quant, +4 more.

vram_probesB
Read-only
Inspect

The raw measured probe rows (RX 7900 XTX and RTX 3060 Ti), filtered by any of the given settings. gpu matches part of the card name, e.g. '7900' or '3060'.

Inputs: gpu, dora, rank, quant, +2 more.

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

    • A
      license
      A
      quality
      B
      maintenance
      LLM deployment planner: given a model and a GPU, answers will it fit, will it hit your SLO, and what will it cost. Sizes VRAM and KV-cache from the model's real architecture, and labels every number measured, estimated, or unknown.
      5
      1,118 PyPI
      3
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Vendor-neutral local LLM inference benchmark and hardware-config advisor for mlx and llama.cpp. Exposes an MCP tool that measures real tokens/second on your own hardware.
      11 npm
      Apache 2.0
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables users to describe a fine-tuning workload once and receive task-aware VRAM/FLOP estimates plus ranked cheapest, fastest, and balanced GPU options across multiple cloud providers. It can be used from Claude Code/Desktop or CLI/API to identify viable hardware options without manually comparing provider pricing.
      -
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources