MarvinLabs vram_fit
Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"vram-fit": {
"url": "https://marvinlabs.org/mcp"
}
}
}遠端端點
https://marvinlabs.org/mcpstreamable-http它能做什麼
工具清單
工具（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.
輸入結構描述
{
"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).
輸入結構描述
{
"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'.
輸入結構描述
{
"type": "object",
"properties": {
"rank": {
"type": "integer"
},
"seq_len": {
"type": "integer"
},
"quant": {
"type": "string"
},
"lora_dropout": {
"type": "number"
},
"dora": {
"type": "boolean"
},
"gpu": {
"type": "string"
}
}
}社群
證據