Lokale LLMs

AUTOMATIC1111

Advanced local Stable Diffusion workflows

• Kostenlos
• Bildgenerierung
• stable-diffusion
• Lokale Inferenz

CogView 4

Developer workflows · Faceless content production

• Kostenlos
• Bildgenerierung
• text-to-image
• Open Weights

ComfyUI TTS

Local custom voiceover pipelines · Experimental multi-model TTS workflows

• Kostenlos
• Text-zu-Sprache
• Voiceover
• narration

Command R+

Advanced local assistant deployments · Complex retrieval and planning workflows

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Coqui TTS

Advanced local text-to-speech pipelines

• Kostenlos
• Text-zu-Sprache
• Voiceover
• Lokale Inferenz

DeepSeek-R1

Reasoning-heavy workflows on distilled checkpoints · Local experimentation with open model pipelines

• Kostenlos
• Lokale Inferenz
• Open Weights
• mit

DeepSeek-VL2

Private visuelle Dokumentanalyse · Multimodales Dokumentverstaendnis

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

FLUX

Thumbnail and visual concept generation · Fast style exploration for creator content

• Kostenlos
• Bildgenerierung
• text-to-image
• image-editing

Fooocus

Fast local image generation with minimal setup

• Kostenlos
• Bildgenerierung
• stable-diffusion
• Lokale Inferenz

Forge

Faster local Stable Diffusion workflows in a linear WebUI

• Kostenlos
• Bildgenerierung
• stable-diffusion
• Lokale Inferenz

Gemma 2

Efficient local chat workloads · Summarization and long-form drafting

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Gemma 3

Lokale Assistenten mit handhabbaren Compliance-Prozessen · Multimodale Zusammenfassung und Extraktion

• Kostenlos
• Lokale Inferenz
• Open Weights
• On-Device

GLM-4.5 Air

Private local LLM workflows · Reasoning and coding support in automation tasks

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

GLM-4.7-Flash

Fast local coding assistants · Reasoning-heavy drafting with tighter latency budgets

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

gpt-oss-20b

Private drafting and extraction workflows · Batch automations with stable cost control

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

HiDream

Thumbnail and visual concept generation · Fast style exploration for creator content

• Kostenlos
• Bildgenerierung
• text-to-image
• image-editing

HunyuanDiT

Developer workflows · Faceless content production

• Kostenlos
• Bildgenerierung
• text-to-image
• Open Weights

InternVL 3.5

Multimodale interne Analyse-Workflows · Builders experimenting with vision-language tasks

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

InvokeAI

Professional local image workflows with cleaner UX

• Kostenlos
• Bildgenerierung
• stable-diffusion
• Lokale Inferenz

Kandinsky 3

Thumbnail and visual concept generation · Faceless content production

• Kostenlos
• Bildgenerierung
• text-to-image
• Open Weights

Kimi K

Local long-context drafting and analysis · Builders comparing open-weight LLM stacks

• Kostenlos
• Lokale Inferenz
• Open Weights
• reasoning

Kokoro TTS

Lightweight local text-to-speech experiments

• Kostenlos
• Text-zu-Sprache
• Voiceover
• Lokale Inferenz

Kolors

Thumbnail and visual concept generation · Faceless content production

• Kostenlos
• Bildgenerierung
• text-to-image
• Open Weights

LatentSync

Free local talking-head generation

• Kostenlos
• avatar-video
• Lokale Inferenz
• open-source

LivePortrait

Local avatar animation workflows

• Kostenlos
• avatar-video
• Lokale Inferenz
• open-source

Llama 3.1

General local chat and assistant workflows · Summarization and drafting tasks

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Llama 3.2 Vision

Lokale Bild-und-Text-Analyse-Workflows · Multimodales Dokumentverstaendnis

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Llama 3.3

High-quality local assistant workflows · Reasoning-heavy long-form tasks

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Llama 4

Pipelines zur Zusammenfassung grosser Dokumentmengen · Multimodale interne Analyse-Workflows

• Kostenlos
• Lokale Inferenz
• Open Weights
• Multimodal

LocalAI

Local model serving and testing · Private local LLM workflows

• Kostenlos
• Lokale Inferenz
• Self-Hosted
• open-source

LocalForge

Local model serving and testing · Private lokale Assistenten-Workflows

• Kostenlos
• Lokale Inferenz
• open-source
• Self-Hosted

MiniCPM-V 2.6

Private visuelle Dokumentanalyse · Multimodale lokale Assistenten-Workflows

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Ministral 3 8B

Zusammenfassung und Extraktion langer Dokumente · Private lokale Assistenten-Workflows

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Mistral NeMo

Balanced local assistant workloads · Coding and reasoning mixed tasks

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Mixtral 8x22B

High-end local inference setups · Long-context reasoning workflows

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Molmo

Multimodales Dokumentverstaendnis · Private visuelle Dokumentanalyse

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

MuseTalk

Free local talking-head generation

• Kostenlos
• avatar-video
• Lokale Inferenz
• open-source

NVIDIA Nemotron

Agentic AI prototyping · Reasoning-heavy developer workflows

• Kostenlos
• Open Weights
• reasoning
• agentic-ai

Ollama

Local model serving and testing · Privacy-first AI workflows

• Kostenlos
• Lokale Inferenz
• Self-Hosted
• offline

Phi-3 Mini

Low-latency local chat and coding help · Entry-level local LLM deployments

• Kostenlos
• Lokale Inferenz
• Open Weights
• On-Device

Phi-3.5 Mini Instruct

Private drafting and summarization on modest hardware · Lightweight offline content automation

• Kostenlos
• Lokale Inferenz
• Open Weights
• On-Device

Phi-3.5 Vision Instruct

Multimodales Dokumentverstaendnis · Private visuelle Dokumentanalyse

• Kostenlos
• Lokale Inferenz
• Open Weights
• On-Device

Phi-4

Reasoning-heavy local workflows · Structured instruction and planning tasks

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Phi-4 Reasoning

Complex reasoning and analytical tasks · Local private inference with explicit step logic

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Piper TTS

Local private text-to-speech pipelines

• Kostenlos
• Text-zu-Sprache
• Voiceover
• Lokale Inferenz

PixArt-Σ

Thumbnail and visual concept generation · Faceless content production

• Kostenlos
• Bildgenerierung
• text-to-image
• Open Weights

Qwen2.5

Multilingual content generation · Long-form drafting and rewriting

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Qwen2.5 VL

Multimodale lokale Assistenten-Workflows · Private visuelle Dokumentanalyse

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

Qwen3 8B

Private local writing and rewriting · Multilingual content transformation

• Kostenlos
• Lokale Inferenz
• Open Weights
• Self-Hosted

SadTalker

Free local talking-head generation

• Kostenlos
• avatar-video
• Lokale Inferenz
• open-source

Stable Diffusion

Faceless content production · Solopreneur operations

• Kostenlos
• Bildgenerierung
• Design
• thumbnails

SwarmUI

Local Stable Diffusion workflows with larger job queues

• Kostenlos
• Bildgenerierung
• stable-diffusion
• Lokale Inferenz

Voicebox

Local custom voiceover pipelines · Advanced local text-to-speech pipelines

• Kostenlos
• Text-zu-Sprache
• voice-cloning
• Lokale Inferenz

Z-Image

Thumbnail and visual concept generation · Fast style exploration for creator content

• Kostenlos
• Bildgenerierung
• text-to-image
• image-editing