list_models
List all local Whisper model files with details on size, activity, quantization, and use case. Reads filesystem-only for offline model management.
Instructions
List all Whisper model files installed in your models directory. Shows filename, size, whether it is currently active, quantization status, and recommended use case for each model. No network calls — reads local filesystem only.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Implementation Reference
- src/index.ts:1080-1088 (registration)Tool 'list_models' is registered in the ListToolsRequestSchema handler with its description and empty inputSchema (no required parameters).
{ name: "list_models", description: "List all Whisper model files installed in your models directory. " + "Shows filename, size, whether it is currently active, quantization status, " + "and recommended use case for each model. " + "No network calls — reads local filesystem only.", inputSchema: { type: "object", properties: {} }, }, - src/index.ts:1300-1356 (handler)Handler for 'list_models' tool: reads the models directory, filters .bin files, displays active model, size, quantization status, and recommended use case from MODEL_REGISTRY. Also lists downloadable models not yet installed.
// list_models // ------------------------------------------------------------------------- if (name === "list_models") { const modelsDir = dirname(WHISPER_MODEL); if (!existsSync(modelsDir)) { return { content: [{ type: "text", text: `Models directory not found: ${modelsDir}` }], isError: true }; } let files: string[]; try { files = readdirSync(modelsDir).filter(f => f.endsWith(".bin")); } catch (err: any) { return { content: [{ type: "text", text: `Could not read models directory: ${err?.message}` }], isError: true }; } if (files.length === 0) { return { content: [{ type: "text", text: `No .bin model files found in: ${modelsDir}\n\n` + `Use download_model to install a model.\n` + `Recommended starting point: large-v3-turbo (English GPU) or large-v3-turbo-q5_0 (CPU/multilingual)`, }], }; } const activeFile = basename(WHISPER_MODEL); const rows = files.map(f => { const fullPath = join(modelsDir, f); const sizeMb = (() => { try { return (statSync(fullPath).size / (1024 * 1024)).toFixed(0) + " MB"; } catch { return "?"; } })(); const isActive = f === activeFile ? " ◀ ACTIVE" : ""; const known = MODEL_REGISTRY.find(m => m.filename === f); const quantTag = known?.quantized ? " [quantized]" : ""; const useCase = known ? known.useCase : "Unknown model"; return `${isActive ? "●" : "○"} ${f}${isActive}${quantTag}\n Size: ${sizeMb} | ${useCase}`; }); // Also list downloadable models not yet installed const installedFilenames = new Set(files); const available = MODEL_REGISTRY .filter(m => !installedFilenames.has(m.filename)) .map(m => ` ${m.name} (${m.filename}, ~${m.sizeMb} MB) — ${m.useCase}`) .join("\n"); return { content: [{ type: "text", text: `Installed models in: ${modelsDir}\n${"─".repeat(60)}\n\n` + rows.join("\n\n") + (available ? `\n\n${"─".repeat(60)}\nAvailable to download:\n${available}\n\nUse download_model <name> to install.` : `\n\n${"─".repeat(60)}\nAll known models are installed.`), }], }; } - src/index.ts:549-579 (helper)MODEL_REGISTRY constant containing metadata for all known Whisper models (name, filename, size, multilingual flag, quantization, use case, download URL) used by list_models to annotate installed files.
interface ModelEntry { name: string; filename: string; sizeMb: number; multilingual: boolean; quantized: boolean; useCase: string; url: string; } const MODEL_REGISTRY: ModelEntry[] = [ // Full-precision English { name: "tiny.en", filename: "ggml-tiny.en.bin", sizeMb: 75, multilingual: false, quantized: false, useCase: "Quick tests, lowest accuracy", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-tiny.en.bin" }, { name: "base.en", filename: "ggml-base.en.bin", sizeMb: 142, multilingual: false, quantized: false, useCase: "Fast English, good accuracy", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin" }, { name: "small.en", filename: "ggml-small.en.bin", sizeMb: 466, multilingual: false, quantized: false, useCase: "Better English accuracy", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.en.bin" }, { name: "medium.en", filename: "ggml-medium.en.bin", sizeMb: 1500, multilingual: false, quantized: false, useCase: "High accuracy English, fast on GPU", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-medium.en.bin" }, // Full-precision multilingual { name: "tiny", filename: "ggml-tiny.bin", sizeMb: 75, multilingual: true, quantized: false, useCase: "Multilingual, minimal accuracy", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-tiny.bin" }, { name: "base", filename: "ggml-base.bin", sizeMb: 142, multilingual: true, quantized: false, useCase: "Multilingual, fast", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin" }, { name: "small", filename: "ggml-small.bin", sizeMb: 466, multilingual: true, quantized: false, useCase: "Multilingual, better accuracy", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin" }, { name: "medium", filename: "ggml-medium.bin", sizeMb: 1500, multilingual: true, quantized: false, useCase: "Multilingual, high accuracy", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-medium.bin" }, { name: "large-v3", filename: "ggml-large-v3.bin", sizeMb: 2900, multilingual: true, quantized: false, useCase: "Best accuracy, multilingual — requires 6GB+ VRAM", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3.bin" }, { name: "large-v3-turbo", filename: "ggml-large-v3-turbo.bin", sizeMb: 1600, multilingual: true, quantized: false, useCase: "~6x faster than large-v3, minimal accuracy loss — RECOMMENDED for English GPU batch work", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3-turbo.bin" }, // Quantized variants — smaller, CPU-friendly { name: "base.en-q5_1", filename: "ggml-base.en-q5_1.bin", sizeMb: 57, multilingual: false, quantized: true, useCase: "Tiny English model, CPU-friendly", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en-q5_1.bin" }, { name: "small.en-q5_1", filename: "ggml-small.en-q5_1.bin", sizeMb: 181, multilingual: false, quantized: true, useCase: "Fast English, low memory, good for CPU", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.en-q5_1.bin" }, { name: "medium.en-q5_0", filename: "ggml-medium.en-q5_0.bin", sizeMb: 514, multilingual: false, quantized: true, useCase: "High accuracy English, CPU-friendly — good default for no-GPU systems", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-medium.en-q5_0.bin" }, { name: "large-v3-q5_0", filename: "ggml-large-v3-q5_0.bin", sizeMb: 1080, multilingual: true, quantized: true, useCase: "Best multilingual quality at half the size", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3-q5_0.bin" }, { name: "large-v3-turbo-q5_0", filename: "ggml-large-v3-turbo-q5_0.bin", sizeMb: 547, multilingual: true, quantized: true, useCase: "RECOMMENDED for CPU-only multilingual — fast, low memory, good accuracy", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3-turbo-q5_0.bin" }, { name: "large-v3-turbo-q8_0", filename: "ggml-large-v3-turbo-q8_0.bin", sizeMb: 874, multilingual: true, quantized: true, useCase: "Turbo quality closer to full precision, moderate size", url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3-turbo-q8_0.bin" }, ];