knowledge-base/wiki/concepts/llm/llm-model-catalog.md

---
created: 2026-06-23
updated: 2026-06-23
sources:
  - concepts/llm/glm-5.2-zai-coding-model.md
  - tools/kimi-k2.7-code.md
  - tools/anthropic-claude.md
  - tools/openai-gpt.md
  - concepts/hardware/cloud-exit-and-local-superiority.md
  - architecture/model-routing.md
  - concepts/llm/real-world-coding-showdown.md
  - concepts/llm/llm-model-fusion-ensembles.md
  - concepts/llm/post-transformer-llm-architectures.md
  - concepts/llm/flat-curve-society.md
  - raw/other/2026-06-19_ome21-briefing-ki-fortschritte-lokale-modelle.md
tags: [concept, llm, model-catalog, local-models, huggingface, ollama, open-source]
---

# LLM Model Catalog — Konsolidierte Modell-Übersicht mit Fokus auf lokale Deployment-Optionen

> **Zweck:** Diese Seite konsolidiert alle im Wiki erwähnten LLM-Modelle in einer referenzierbaren Übersicht. Schwerpunkt liegt auf **lokal deploybaren Modellen** (Open Weights, Ollama, LM Studio etc.), da Cloud-Exit und lokale Überlegenheit — wie im OME21-Debrief und Yegges Flat-Curve-These dokumentiert — die strategisch relevanteste Entwicklung 2026 ist. Attribution: Wer hat welches Modell im Wiki oder OME-Kontext getestet? HuggingFace-Links wo dokumentiert.

---

## 1. Frontier-Modelle (Cloud-only, Closed Weights)

Diese Modelle sind proprietär, nicht lokal hostbar, und werden über API-Provider (OpenRouter, direkte APIs, OpenClaw Provider-Adapter) geroutet. Sie dienen als Benchmark-Referenz und Qualitäts-Benchmark für Open-Source-Alternativen.

| Modell | Hersteller | Kontext | Preis | Lizenz | Bemerkung | Quelle |
|--------|-----------|---------|-------|--------|-----------|--------|
| Claude Opus 4.8 | Anthropic | — | — | Closed | Aktuelles Frontier-Modell (GA). $30 Mrd. ARR, 500+ Enterprise-Kunden. Nicht von Exportkontrollen betroffen. | [[../../tools/anthropic-claude.md]] |
| Claude Fable 5 | Anthropic | — | — | Closed | Public-Version von Mythos 5 (ohne Cybersecurity-Safeguards). Launch 9. Juni 2026, 3 Tage später blockiert. DRACO-Solo: 65.3% (93/100 Tasks, 7 durch Content-Filter abgebrochen). | [[../../tools/anthropic-claude.md]], [[llm-model-fusion-ensembles.md]] |
| Claude Mythos 5 | Anthropic | — | — | Closed | Cybersecurity-Spezialmodell, NSA nutzt es für offensive Cyber-Ops. Export-restricted seit 12.06.2026. | [[../../tools/anthropic-claude.md]] |
| Claude Opus 4.7 | Anthropic | — | — | Closed | Legacy-Vorgängermodell. | [[../../tools/anthropic-claude.md]] |
| GPT-5.5 | OpenAI | 1M | $5/$30 pro Mio I/O | Closed | "Smartest and most intuitive model yet". Agentic Coding, Computer Use. Released 2026-04-23. DRACO-Solo: 60.0%. | [[../../tools/openai-gpt.md]], [[llm-model-fusion-ensembles.md]] |
| GPT-5.5 Instant | OpenAI | — | — | Closed | 52,5% weniger Halluzinationen (Medizin, Jura, Finanzen). Released 2026-05-05. | [[../../tools/openai-gpt.md]] |
| GPT-5.4 | OpenAI | 200K | — | Closed | Routing: `openrouter/openai/gpt-5.4`. 32K Output. Reasoning/Thinking deaktiviert (per Claire Vo-Empfehlung). | [[../../architecture/model-routing.md]] |
| Grok 4.20 | xAI | — | — | Closed | Routing: `xai/grok-4.20-0309-non-reasoning`. Ideation-Phase in Two-Model-Pipeline (Grok → Gemini). | [[../../architecture/model-routing.md]] |
| Gemini 3.1 Pro | Google | — | — | Closed | DRACO-Solo: 45.4%. Kosteneffizient für Enterprise, Cloud-Integration. | [[../../tools/openai-gpt.md]], [[llm-model-fusion-ensembles.md]] |
| Gemini 3 Flash | Google | — | — | Closed | DRACO-Solo: 43.1%. Routing: `ollama/gemini-3-flash-preview`. Synthesis-Phase in Two-Model-Pipeline. | [[llm-model-fusion-ensembles.md]], [[../../architecture/model-routing.md]] |

> **Strategisches Bild:** Yegges Flat-Curve-These ([[flat-curve-society.md]]) besagt, dass Frontier-Modelle in 2-3 Generationen unter Lockdown geraten — kontrolliert wie Kernwaffen, zugänglich nur als "vending machine". OSS-Modelle trailn Frontier um ~7 Monate. Die praktische Konsequenz: **"Route every task to the dumbest model that can handle it"** — Discernment Horizon als Routing-Infrastruktur.

---

## 2. Open-Source / Local-Deployable Modelle

Das Herzstück. Modelle mit Open Weights oder zumindest lokaler Hosting-Option. Sortiert nach Relevanz für das RamaDama-Setup.

| Modell | Hersteller | Architektur | Kontext | Lizenz | HuggingFace | Lokale Hosting | Getestet von | Praxis-Erfahrung | Tokens/s | Quelle |
|--------|-----------|-------------|---------|--------|-------------|----------------|-------------|-------------------|----------|--------|
| **GLM 5.2** | Zhipu AI / [Z.ai](https://z.ai/) | Dense, 744B | 1M | MIT | https://huggingface.co/zai-org/GLM-5 | LM Studio, Unsloth, DwarfStar (antirez/ds4), Ollama, OpenClaw v2026.6.8 | IAmFabian (Flappy Bird, Newton-Pendel, 14.06.2026), AI mit Arnie (4 Tests, 22.06.2026), Fahd Mirza (Head-to-Head vs Kimi K2.7, 14.06.2026), Hector (`ollama/glm-5.2:cloud`) | Frontier-Niveau, vergleichbar mit Opus 4.6 (6% darunter laut AI Code King). Stärke: kreative Animation, Detail. Schwäche: Light-Plan-Wartezeiten, Innovation bei Bug-Fix geringer als Kimi. 10× günstiger als Claude. | — | [[glm-5.2-zai-coding-model.md]], [[real-world-coding-showdown.md]] |
| **GLM 5.1** | Zhipu AI / Z.ai | — | 200K | — | — | Ollama, OpenClaw | Hector (`ollama/glm-5.1`) | Geplant als neuer Primary in Hectors Routing (Stand 16.06.2026). | — | [[../../architecture/model-routing.md]] |
| **GLM 5.0** | Zhipu AI / Z.ai | — | 200K | — | — | Ollama (`zai/glm-5-turbo`) | — | Vorgänger, Feb 2026. In alter Fallback-Chain als zweite Stufe. | — | [[glm-5.2-zai-coding-model.md]], [[../../architecture/model-routing.md]] |
| **Kimi K2.7 Code** | Moonshot AI | MoE, ~1.04T (1T total, 32B active) | 256K | Open | — | Ollama Cloud (NVIDIA B300), Ollama local, `ollama launch` (Claude, OpenClaw, Codex, Hermes, OpenCode) | Fahd Mirza (Head-to-Head vs GLM-5.2, 14.06.2026), Hector (`ollama/kimi-k2.7-code`) | ~30% weniger Thinking-Tokens als K2.6. Stärke: Speed (~5 Min für Bug-Fix+Feature), Innovation (Progression-Previews). Schwäche: Animation sehr schwach. MCP Mark Verified: 81.1 (schlägt Claude 76.4). | — | [[../../tools/kimi-k2.7-code.md]], [[real-world-coding-showdown.md]] |
| **Kimi K2.6** | Moonshot AI | — | — | Open | — | OpenRouter | OpenRouter (DRACO-Benchmark) | DRACO-Solo: 53.7%. Budget-Panel-Kandidat in OpenRouter Fusion. | — | [[llm-model-fusion-ensembles.md]] |
| **DeepSeek V4 Pro** | DeepSeek | — | — | — | — | OpenRouter, Ollama (`ollama/deepseek-v4-pro:cloud`) | OpenRouter (DRACO-Benchmark), Hector | DRACO-Solo: 60.3%. Budget-Panel: Gemini 3 Flash + Kimi K2.6 + DeepSeek V4 Pro = 64.7% (bei 50% Kosten vs Fable 5). | — | [[llm-model-fusion-ensembles.md]] |
| **DeepSeek V4 Flash** | DeepSeek | — | — | — | — | Ollama (`ollama/deepseek-v4-flash:cloud`) | Hector | Cloud-Variante im aktiven Stack. | — | MEMORY.md (Hector's Setup) |
| **DeepSeek V3.2** | DeepSeek | — | — | — | — | Ollama | Hector | Aktiver Ollama-Provider. | — | MEMORY.md (Hector's Setup) |
| **NLS 2.5** | nicht dokumentiert | MoE (1,5 Mrd. Parameter pro Expert) | — | — | — | Local (MacBook Pro M-Series) | OME21 Community | 150 Tokens/s lokal — Gemini-Flash-Niveau offline. | **150** | [[../hardware/cloud-exit-and-local-superiority.md]] |
| **Qwen 3.5 Vision** | Qwen (Alibaba) | Vision/OCR | — | — | — | Local (MacBook Pro M-Series) | OME21 Community | Lokales OCR, visuelle Verarbeitung. 80 Tokens/s lokal. | **80** | [[../hardware/cloud-exit-and-local-superiority.md]] |
| **Qwen3 Coder (480B)** | Qwen (Alibaba) | — | — | — | — | Ollama (`ollama/qwen3-coder:480b`) | Hector | Aktiver Ollama-Provider. | — | MEMORY.md (Hector's Setup) |
| **Qwen 3.5 (397B)** | Qwen (Alibaba) | — | — | — | — | Ollama (`ollama/qwen3.5:397b`) | Hector | Aktiver Ollama-Provider. | — | MEMORY.md (Hector's Setup) |
| **MiniMax M3** | MiniMax | — | — | — | — | Ollama (`ollama/minimax-m3`) | Hector (Wiki-Kuration via Ollama) | Geplanter Fallback hinter GLM-5.1 Primary. OME21: "Hochwertige autonome Kuration extrem kosteneffizient" — nur 20% Token-Kontingent nach Monatsmitte. | — | [[../../architecture/model-routing.md]], [[../../../raw/other/2026-06-19_ome21-briefing-ki-fortschritte-lokale-modelle.md]] |
| **MiniMax M2.7** | MiniMax | — | — | — | — | Ollama (`ollama/minimax-m2.7`) | Hector | Legacy-Fallback (letzte Stufe der alten Fallback-Chain). | — | [[../../architecture/model-routing.md]], MEMORY.md |
| **Nemotron 3 Ultra** | NVIDIA | — | — | — | — | Ollama (`ollama/nemotron-3-ultra`) | Hector | Aktiver Ollama-Provider. | — | MEMORY.md (Hector's Setup) |
| **GPT-OSS 120B** | OpenAI | — | — | — | — | Ollama (`ollama/gpt-oss:120b`) | Hector | Aktiver Ollama-Provider. OpenAI's Open-Source-Modell. | — | MEMORY.md (Hector's Setup) |
| **MiMo v2 Pro** | Xiaomi | — | — | — | — | OpenRouter (`openrouter/xiaomi/mimo-v2-pro`) | Hector | Aktiver OpenRouter-Provider. | — | MEMORY.md (Hector's Setup) |
| **Gemini 3 Flash** | Google | — | — | — | — | Ollama (`ollama/gemini-3-flash-preview`) | Hector, OpenRouter (DRACO) | DRACO-Solo: 43.1%. Budget-Panel-Kandidat. Synthesis-Phase in Two-Model-Pipeline. | — | [[../../architecture/model-routing.md]], [[llm-model-fusion-ensembles.md]] |

> **Lokale Performance-Referenz:** OME21-Debrief ([[../hardware/cloud-exit-and-local-superiority.md]]): Apple M-Series mit 48-128 GB RAM erreicht mit MoE-Modellen Geschwindigkeiten auf Gemini-Flash-Niveau — komplett offline. RAM wird zur neuen digitalen Währung; 48 GB kritische Untergrenze, 64-128 GB empfohlen.

### Community-Krallen im Einsatz (OME21)

| Operator | Anwendung | Modell | DSGVO | Quelle |
|----------|-----------|--------|-------|--------|
| Rüdiger | Zeugniserstellung (Schulwesen) | Gemini 3.5 Flash lokal | 100% | [[../hardware/cloud-exit-and-local-superiority.md]] |
| Andreas | E-Book-Vektorisierung (persönl. RAG) | Server-Pipeline | — | [[../hardware/cloud-exit-and-local-superiority.md]] |
| Christian | SLA-Übersetzung (juristisch) | Kimi lokal | — | [[../hardware/cloud-exit-and-local-superiority.md]] |
| Hector | Autonomes Gruppen-Wiki | MiniMax 3.0 via Ollama | — | [[../../../raw/other/2026-06-19_ome21-briefing-ki-fortschritte-lokale-modelle.md]] |

---

## 3. Hector's Active Stack

Hectors Modell-Routing gemäß [[../../architecture/model-routing.md]] und MEMORY.md (Stand 23.06.2026).

### Routing-Architektur

```
Primary (geplant):   ollama/glm-5.1
Fallback:            ollama/minimax-m3
Long-Context (1M):   ollama/glm-5.2:cloud
Coding:              ollama/kimi-k2.7-code
Ideation:            xai/grok-4.20-0309-non-reasoning
Synthesis:           ollama/gemini-3-flash-preview
Frontier Quality:    Claude Opus 4.8 / Fable (via OpenRouter)
```

**Alte Fallback-Chain (wird abgelöst):**
```
openrouter/auto → zai/glm-5-turbo → moonshot/moonshot-v1-auto
  → moonshot/kimi-k2.5 → ollama/minimax-m2.7
```

### Vollständige Active Provider-Tabelle

| Modell | Provider-Route | Rolle | Kontext | Quelle |
|--------|---------------|-------|---------|--------|
| GLM-5.2 Cloud | `ollama/glm-5.2:cloud` | Active (Runtime) | 1M | [[glm-5.2-zai-coding-model.md]] |
| GLM-5.1 Cloud | `ollama/glm-5.1` | Primary (Migration) | 200K | [[../../architecture/model-routing.md]] |
| GLM-5 | `ollama/glm-5` | Active | — | MEMORY.md |
| MiniMax M3 | `ollama/minimax-m3` | Fallback | — | [[../../architecture/model-routing.md]] |
| MiniMax M2.7 | `ollama/minimax-m2.7` | Legacy Fallback | — | [[../../architecture/model-routing.md]] |
| Kimi K2.7 Code | `ollama/kimi-k2.7-code` | Coding | 256K | [[../../tools/kimi-k2.7-code.md]] |
| DeepSeek V3.2 | `ollama/deepseek-v3.2` | Active | — | MEMORY.md |
| DeepSeek V4 Flash | `ollama/deepseek-v4-flash:cloud` | Active (Cloud) | — | MEMORY.md |
| DeepSeek V4 Pro | `ollama/deepseek-v4-pro:cloud` | Active (Cloud) | — | MEMORY.md |
| Qwen 3.5 (397B) | `ollama/qwen3.5:397b` | Active | — | MEMORY.md |
| Qwen3 Coder (480B) | `ollama/qwen3-coder:480b` | Active | — | MEMORY.md |
| Nemotron 3 Ultra | `ollama/nemotron-3-ultra` | Active | — | MEMORY.md |
| GPT-OSS 120B | `ollama/gpt-oss:120b` | Active | — | MEMORY.md |
| Gemini 3 Flash | `ollama/gemini-3-flash-preview` | Synthesis | — | [[../../architecture/model-routing.md]] |
| GPT-5.4 | `openrouter/openai/gpt-5.4` | Active (OpenRouter) | 200K / 32K Output | [[../../architecture/model-routing.md]] |
| Grok 4.20 | `xai/grok-4.20-0309-non-reasoning` | Ideation | — | [[../../architecture/model-routing.md]] |
| MiMo v2 Pro | `openrouter/xiaomi/mimo-v2-pro` | Active (OpenRouter) | — | MEMORY.md |

### Sub-Task-Routing-Plan

```
OpenClaw Primary Routing
  ├─ Creative / Long-Context (1M)  → GLM 5.2 (via OpenClaw provider-adapter)
  ├─ Speed / Innovation Coding     → Kimi K2.7 Code
  ├─ Standard Tasks                → openrouter/auto → ollama/minimax-m3
  └─ Frontier Quality              → Claude Opus 4.8 / Fable
```

*Quelle: [[../../architecture/model-routing.md]] — Update 2026-06-16 nach OpenClaw v2026.6.8*

---

## 4. Post-Transformer-Architekturen (Outlook)

Nicht im aktiven Routing, aber mittelfristig zu beobachten. Status: **beobachten, nicht adoptieren.** Keine offenen Weights + stabile Provider-Listings bisher.

| Architektur | Kernidee | Status | Quelle |
|-------------|----------|--------|--------|
| **Griffin** | Lokale Attention + rekurrentes "Index-Karten"-Gedächtnis statt KV-Cache. [arXiv:2402.19427](https://arxiv.org/abs/2402.19427) | Veröffentlicht 2024 | [[post-transformer-llm-architectures.md]] |
| **Recurrent Gemma** | Baut auf Griffin auf; verbesserte Langkontext-Benchmarks. [arXiv:2404.08239](https://arxiv.org/abs/2404.08239) | 2024 | [[post-transformer-llm-architectures.md]] |
| **Titans** | "Learning to Memorize at Test Time" — selektives Gedächtnis. [arXiv:2501.00663](https://arxiv.org/abs/2501.00663) | Behrouz et al., 2025 | [[post-transformer-llm-architectures.md]] |
| **Gemma 4** | Sparsity/Experts + lokal+global hybrid multimodal. 256k Token auf Edge-Hardware. | Aktuell | [[post-transformer-llm-architectures.md]] |
| **Gemini Diffusion** | Iterative Sequenz-Verfeinerung statt AR. ~10× schneller bei ähnlicher Qualität. Beliebige Kontextpositionen (Code-Completion in Lücken). | Ankündigung Mai 2025 | [[post-transformer-llm-architectures.md]] |
| **V-JEPA** | JEPA-Weltmodell (Meta/LeCun): Konsistenz von Repräsentationen statt Pixel-Rekonstruktion. [arXiv:2404.08471](https://arxiv.org/abs/2404.08471) | Empirisch noch hinter Top-Generatoren | [[post-transformer-llm-architectures.md]] |

**OpenClaw-Relevanz:** Mittelfristig könnten Griffin-artige Architekturen für lokal laufende Embedding/SSR-Modelle interessant werden. Diffusions-LLMs für parallele Code-Completion in nicht-Präfix-Positionen (Hermes-Agent-Code-Edit-Tasks). JEPA für Subconscious-Agent-"Simulations-Prior".

---

## 5. Ensemble- und Fusion-Kontext

OpenRouter Fusion ([[llm-model-fusion-ensembles.md]]) ermöglicht parallele Model-Panels mit Judge-Synthese. DRACO-Benchmark-Ergebnisse:

| Typ | Model(s) | Synthesizer | DRACO Score |
|-----|----------|-------------|-------------|
| Fusion | Fable 5 + GPT-5.5 | Opus 4.8 | **69.0%** |
| Fusion | Opus 4.8 + GPT-5.5 + Gemini 3.1 Pro | Opus 4.8 | **68.3%** |
| Fusion | Opus 4.8 + GPT-5.5 | Opus 4.8 | **67.6%** |
| Fusion | Opus 4.8 + Opus 4.8 (Self-Fusion) | Opus 4.8 | **65.5%** |
| Solo | Fable 5 | — | 65.3% |
| **Budget-Fusion** | Gemini 3 Flash + Kimi K2.6 + DeepSeek V4 Pro | Opus 4.8 | **64.7%** |
| Solo | DeepSeek V4 Pro | — | 60.3% |
| Solo | GPT-5.5 | — | 60.0% |
| Solo | Claude Opus 4.8 | — | 58.8% |
| Solo | Kimi K2.6 | — | 53.7% |
| Solo | Gemini 3.1 Pro | — | 45.4% |
| Solo | Gemini 3 Flash | — | 43.1% |

**Kernerkenntnis:** Budget-Panels (Open-Source-Modelle) erreichen Frontier-Nähe zu halben Kosten. GLM 5.2 + Kimi K2.7 als heterogenes Coding-Panel (Dense vs MoE) ist Ensemble-Kandidat.

---

## Quellen

### Wiki-Seiten (referenziert)

- [[glm-5.2-zai-coding-model.md]] — GLM 5.2: Distribution, Tests, OpenClaw-Integration, Self-Hosting-Pfade
- [[../../tools/kimi-k2.7-code.md]] — Kimi K2.7 Code: Benchmarks, Ollama Cloud, Verbesserungen über K2.6
- [[../../tools/anthropic-claude.md]] — Claude-Modellfamilie: Opus 4.8, Mythos/Fable 5, Exportkontrollen
- [[../../tools/openai-gpt.md]] — GPT-5.5, GPT-5.5 Instant, Pricing
- [[../hardware/cloud-exit-and-local-superiority.md]] — Lokale Performance-Parität, NLS 2.5, Qwen 3.5 Vision, RAM als Währung
- [[../../architecture/model-routing.md]] — Two-Model-Pipeline, Fallback-Chain, GLM-5.2-Routing-Position, OpenClaw v2026.6.8
- [[real-world-coding-showdown.md]] — Head-to-Head Kimi K2.7 vs GLM-5.2 in Hermes Agent
- [[llm-model-fusion-ensembles.md]] — OpenRouter Fusion, DRACO-Benchmark, Budget-Panels
- [[post-transformer-llm-architectures.md]] — Griffin, Recurrent Gemma, Titans, Diffusions-LLMs, JEPA
- [[flat-curve-society.md]] — Yegge's Modell-Lockdown-These, Discernment Horizon, "Route to dumbest model"
- [[../../../raw/other/2026-06-19_ome21-briefing-ki-fortschritte-lokale-modelle.md]] — OME21 Community-Krallen, lokale MoE-Benchmarks

### Externe Referenzen

- [Open LLM Leaderboard (HuggingFace)](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
- [OpenRouter Model Listing](https://openrouter.ai/models)
- [Ollama Model Library](https://ollama.com/library)
- [Z.ai (Hersteller GLM)](https://z.ai/)
- [Moonshot AI (Hersteller Kimi)](https://www.moonshot.cn/)
- [GLM-5 Open Weights (HuggingFace)](https://huggingface.co/zai-org/GLM-5)

---

## Cross-References

- [[../../architecture/model-routing.md]] — Wie Modelle im Agent-Stack eingebunden sind (Primary/Fallback/Routing-Plan)
- [[llm-model-fusion-ensembles.md]] — Ensemble-Pattern mit DRACO-Benchmark
- [[real-world-coding-showdown.md]] — Praxis-Vergleich Kimi K2.7 vs GLM-5.2
- [[../hardware/cloud-exit-and-local-superiority.md]] — Warum lokale Modelle 2026 strategisch dominant werden
- [[flat-curve-society.md]] — Warum Frontier-Lockdown OSS-Modelle aufwertet
- [[post-transformer-llm-architectures.md]] — Architektur-Ausblick jenseits AR-Transformer
- [[ai-intelligence-commoditization-thesis.md]] — Makro-These: Modelle werden Commodity
- [[../../tools/anthropic-claude.md]] — Frontier-Referenz (Opus 4.8, Fable 5)
- [[../../tools/openai-gpt.md]] — Frontier-Referenz (GPT-5.5)
- [[../../tools/kimi-k2.7-code.md]] — Detailseite Kimi K2.7
- [[../../tools/hermes-desktop.md]] — Agent-Framework mit Model-Picker
- [[../directives/pro-leben-directive.md]] — Philosophischer Rahmen: Cloud-Exit = Handlungsfähigkeit