Hitonabi
8e4aca9f5c
Katalog-Daten (models_catalog.json) waren teil-stale (Stand 27.06.): - vision: Qwen3-VL-30B-A3B-Instruct ergaenzt (neue Augen, MoE 30B-A3B) — sonst empfahl der "Modelle finden"-Tab weiter das aeltere VL-8B (Downgrade). - scout: gemma-4-26B/31B (laengst entfernt) durch das live genutzte GLM-4.6V-Flash ersetzt. - version 2026-06-27 -> 2026-07-03. Bewusst NICHT aufgenommen: Qwen3.6-27B dense — im 3-Wege-Bench (tg 12,7 vs 60-91 der MoE-Coder) als Coder-Worker unterlegen, keine Empfehlung. Badge-Fix (Discover.tsx): installedModel matchte nur das primaere role-Feld; ein Modell kann eine Kategorie aber ueber einen Alias bedienen (Qwen3.6 = role "hermes" + Alias "fast") -> Fast-Karte zeigte faelschlich "Frei". Jetzt Match per Rolle ODER Alias. Live gegen die Box verifiziert: alle 5 Rollen-Karten "Aktiviert". Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
61 lines
3.4 KiB
JSON
61 lines
3.4 KiB
JSON
{
|
|
"_comment": "Kuratierter Modell-Katalog (Cookbook) für Strix Halo / Ryzen AI MAX+ 395 — 128GB unified, bandbreiten-limitiert (256 GB/s). MoE-first. EINE Quelle der Wahrheit für KORREKTE Metadaten (total/active params, moe, generation) → präzise Empfehlungen ohne Namens-Raterei. Inspiriert vom Odysseus-Cookbook (statischer, validierter Katalog statt Live-Scraping). Erweiterbar: neue Modelle hier eintragen. Felder: name (Match-Identifier), repo (HF org/name für Install), family (+Subtyp), generation (numerisch, für Upgrade-Vergleich), total_params_b, active_params_b (=total bei dense), moe, quant, ctx (empfohlen), tools, vision.",
|
|
"version": "2026-07-03",
|
|
"models": [
|
|
{
|
|
"role": "fast", "name": "Qwen3.6-35B-A3B", "repo": "Qwen/Qwen3.6-35B-A3B-GGUF",
|
|
"family": "qwen", "generation": 3.6, "total_params_b": 35, "active_params_b": 3,
|
|
"moe": true, "quant": "Q4_K_M", "ctx": 32768, "tools": true, "vision": true
|
|
},
|
|
{
|
|
"role": "fast", "name": "Qwen3-30B-A3B-Instruct", "repo": "unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF",
|
|
"family": "qwen", "generation": 3.0, "total_params_b": 30, "active_params_b": 3,
|
|
"moe": true, "quant": "Q4_K_M", "ctx": 32768, "tools": true, "vision": false
|
|
},
|
|
|
|
{
|
|
"role": "heavy", "name": "Qwen3.5-122B-A10B", "repo": "Qwen/Qwen3.5-122B-A10B-GGUF",
|
|
"family": "qwen", "generation": 3.5, "total_params_b": 122, "active_params_b": 10,
|
|
"moe": true, "quant": "Q4_K_M", "ctx": 32768, "tools": true, "vision": false
|
|
},
|
|
{
|
|
"role": "heavy", "name": "gpt-oss-120b", "repo": "ggml-org/gpt-oss-120b-GGUF",
|
|
"family": "gpt-oss", "generation": 1.0, "total_params_b": 120, "active_params_b": 5,
|
|
"moe": true, "quant": "MXFP4", "ctx": 32768, "tools": true, "vision": false
|
|
},
|
|
|
|
{
|
|
"role": "coder", "name": "Qwen3-Coder-Next", "repo": "Qwen/Qwen3-Coder-Next-GGUF",
|
|
"family": "qwen-coder", "generation": 3.0, "total_params_b": 84, "active_params_b": 3,
|
|
"moe": true, "quant": "Q4_K_M", "ctx": 65536, "tools": true, "vision": false
|
|
},
|
|
{
|
|
"role": "coder", "name": "Qwen3-Coder-30B-A3B-Instruct", "repo": "unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF",
|
|
"family": "qwen-coder", "generation": 3.0, "total_params_b": 30, "active_params_b": 3,
|
|
"moe": true, "quant": "Q4_K_M", "ctx": 65536, "tools": true, "vision": false
|
|
},
|
|
|
|
{
|
|
"role": "vision", "name": "Qwen3-VL-30B-A3B-Instruct", "repo": "Qwen/Qwen3-VL-30B-A3B-Instruct-GGUF",
|
|
"family": "qwen-vl", "generation": 3.0, "total_params_b": 30, "active_params_b": 3,
|
|
"moe": true, "quant": "Q4_K_M", "ctx": 32768, "tools": false, "vision": true
|
|
},
|
|
{
|
|
"role": "vision", "name": "Qwen3-VL-8B-Instruct", "repo": "Qwen/Qwen3-VL-8B-Instruct-GGUF",
|
|
"family": "qwen-vl", "generation": 3.0, "total_params_b": 8, "active_params_b": 8,
|
|
"moe": false, "quant": "Q4_K_M", "ctx": 32768, "tools": false, "vision": true
|
|
},
|
|
{
|
|
"role": "vision", "name": "Qwen3-VL-2B-Instruct", "repo": "Qwen/Qwen3-VL-2B-Instruct-GGUF",
|
|
"family": "qwen-vl", "generation": 3.0, "total_params_b": 2, "active_params_b": 2,
|
|
"moe": false, "quant": "Q4_K_M", "ctx": 32768, "tools": false, "vision": true
|
|
},
|
|
|
|
{
|
|
"role": "scout", "name": "GLM-4.6V-Flash", "repo": "ggml-org/GLM-4.6V-Flash-GGUF",
|
|
"family": "glm", "generation": 4.6, "total_params_b": 9, "active_params_b": 3,
|
|
"moe": true, "quant": "Q4_K_M", "ctx": 32768, "tools": true, "vision": true
|
|
}
|
|
]
|
|
}
|