MarvinLabs vram_fit
Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"vram-fit": {
"url": "https://marvinlabs.org/mcp"
}
}
}リモートエンドポイント
https://marvinlabs.org/mcpstreamable-httpできること
ツール一覧
ツール（3）
🟢vram_fit(vram_gb, rank, seq_len, response_len, quant, ...)
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.
入力スキーマ
{
"type": "object",
"properties": {
"vram_gb": {
"type": "number",
"description": "Card memory as sold, in GB (8, 12, 16, 24...)"
},
"rank": {
"type": "integer",
"minimum": 1
},
"seq_len": {
"type": "integer",
"default": 7177,
"description": "Longest training example, in tokens"
},
"response_len": {
"type": "integer",
"default": 237,
"description": "Tokens the loss covers (the response span)"
},
"quant": {
"type": "string",
"enum": [
"4bit",
"bf16"
],
"default": "4bit",
"description": "Base weights: bitsandbytes nf4 or bf16"
},
"lora_dropout": {
"type": "number",
"default": 0
},
"dora": {
"type": "boolean",
"default": false
},
"other_processes_mb": {
"type": "number",
"default": 0,
"description": "VRAM already held by other programs"
},
"model": {
"type": "string",
"default": "unsloth/gemma-3-4b-it"
},
"os": {
"type": "string",
"default": "linux",
"description": "windows or linux; Windows spills instead of OOM"
}
},
"required": [
"vram_gb",
"rank"
]
}🟢vram_max_rank(vram_gb, seq_len, response_len, quant, lora_dropout, ...)
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).
入力スキーマ
{
"type": "object",
"properties": {
"vram_gb": {
"type": "number",
"description": "Card memory as sold, in GB (8, 12, 16, 24...)"
},
"seq_len": {
"type": "integer",
"default": 7177,
"description": "Longest training example, in tokens"
},
"response_len": {
"type": "integer",
"default": 237,
"description": "Tokens the loss covers (the response span)"
},
"quant": {
"type": "string",
"enum": [
"4bit",
"bf16"
],
"default": "4bit",
"description": "Base weights: bitsandbytes nf4 or bf16"
},
"lora_dropout": {
"type": "number",
"default": 0
},
"dora": {
"type": "boolean",
"default": false
},
"other_processes_mb": {
"type": "number",
"default": 0,
"description": "VRAM already held by other programs"
},
"model": {
"type": "string",
"default": "unsloth/gemma-3-4b-it"
}
},
"required": [
"vram_gb"
]
}🟢vram_probes(rank, seq_len, quant, lora_dropout, dora, ...)
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'.
入力スキーマ
{
"type": "object",
"properties": {
"rank": {
"type": "integer"
},
"seq_len": {
"type": "integer"
},
"quant": {
"type": "string"
},
"lora_dropout": {
"type": "number"
},
"dora": {
"type": "boolean"
},
"gpu": {
"type": "string"
}
}
}コミュニティ
エビデンス