MarvinLabs vram_fit
Server Details
Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
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.
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.
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.
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 toolsvram_fitARead-onlyInspect
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_rankBRead-onlyInspect
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_probesBRead-onlyInspect
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
Will a local LLM run on your hardware? GGUF quant, buy-vs-rent-vs-API cost, used-GPU prices.
Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
Does an LLM fit on your GPU? VRAM, KV cache and GPU count for any Hugging Face model.
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
Related MCP Servers
- AlicenseAqualityBmaintenanceLLM 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.51,118 PyPI3MIT
- AlicenseNot gradedqualityAmaintenanceWill this AI model fit on your Mac?94 npm9MIT
- AlicenseNot gradedqualityBmaintenanceVendor-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 npmApache 2.0
- FlicenseNot gradedqualityAmaintenanceEnables 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.-
Glama MCP Gateway
Add one secure layer between your agents and this server.