Model Registry

16 models ready to run. On-device, cross-platform.

Showing 16 of 16 models

Text Generation gguf

Gemma 3 1B

Gemma 3 1B - Google's mobile-optimized instruction-tuned LLM with 32K context

Google 1B params 749.4 MB
Text Generation gguf

Gemma3npc 1B

Gemma3NPC 1B - Mobile-friendly NPC roleplay fine-tune of Gemma 3 1B for in-character game dialogue

Google 1B params 806.0 MB
Text Generation gguf

Gemma3npc It

Gemma3NPC-it - NPC roleplay fine-tune of Gemma3n-E4B for in-character game dialogue

Google 7B params 3.8 GB
Text to Speech onnx

Kitten Tts Micro 0.8

KittenTTS Micro 0.8 - Compact StyleTTS 2 (40M params, 8 named voices)

KittenML 40M params 35.9 MB
Text to Speech onnx

Kitten Tts Mini 0.8

KittenTTS Mini 0.8 - High-quality StyleTTS 2 (80M params, 8 named voices)

KittenML 80M params 56.9 MB
Text to Speech onnx

Kitten Tts Nano 0.2

KittenTTS Nano 0.2 - Ultra-lightweight TTS (15M params, <25MB)

KittenML 15M params 18.3 MB
Text to Speech onnx

Kitten Tts Nano 0.8

KittenTTS Nano 0.8 - Ultra-lightweight StyleTTS 2 (15M params, 8 named voices, OpenPhonemizer)

KittenML 15M params 78.3 MB
Text to Speech onnx

Kokoro 82M

Kokoro 82M - High-quality TTS with 24 voices, Misaki dictionary

Hexgrad 82M params 174.9 MB
Text Generation gguf

Llama 3.2 1B

Llama 3.2 1B - Meta's lightweight mobile-optimized instruction-tuned LLM with 128K context

Meta 1B params 754.3 MB
Text Generation gguf

Ministral 3 3B

Ministral 3 3B Instruct - Mistral AI's edge-optimized instruction-tuned LLM with 256K context

Mistral 3.4B params 2.0 GB
Text Generation gguf

Mistral 7B

Mistral 7B Instruct v0.3 - High-quality desktop LLM with function calling support

Mistral 7B params 4.0 GB
Text Generation gguf

Phi4 Mini

Phi-4 Mini 3.8B - Microsoft's compact reasoning LLM with 128K context

Microsoft 3.8B params 8.1 GB
Text Generation gguf

Qwen2.5 0.5B Instruct

Qwen 2.5 0.5B Instruct - Small but capable instruction-tuned LLM from Alibaba Cloud

Qwen 500M params 455.2 MB
Text Generation gguf

Smollm2 360M

SmolLM2 360M - HuggingFace's best tiny LLM, excellent quality/size ratio

HuggingFace 360M params 254.2 MB
Speech Recognition onnx

Wav2vec2 Base 960H

Wav2Vec2 Base 960h - English ASR with CTC decoding

Meta 95M params 220.3 MB
Speech Recognition safetensors

Whisper Tiny

Whisper Tiny - Fast multilingual ASR (Candle/SafeTensors runtime)

OpenAI 39M params 84.7 MB