Model Registry
16 models ready to run. On-device, cross-platform.
Showing 16 of 16 models
Gemma 3 1B
Gemma 3 1B - Google's mobile-optimized instruction-tuned LLM with 32K context
Gemma3npc 1B
Gemma3NPC 1B - Mobile-friendly NPC roleplay fine-tune of Gemma 3 1B for in-character game dialogue
Gemma3npc It
Gemma3NPC-it - NPC roleplay fine-tune of Gemma3n-E4B for in-character game dialogue
Kitten Tts Micro 0.8
KittenTTS Micro 0.8 - Compact StyleTTS 2 (40M params, 8 named voices)
Kitten Tts Mini 0.8
KittenTTS Mini 0.8 - High-quality StyleTTS 2 (80M params, 8 named voices)
Kitten Tts Nano 0.2
KittenTTS Nano 0.2 - Ultra-lightweight TTS (15M params, <25MB)
Kitten Tts Nano 0.8
KittenTTS Nano 0.8 - Ultra-lightweight StyleTTS 2 (15M params, 8 named voices, OpenPhonemizer)
Kokoro 82M
Kokoro 82M - High-quality TTS with 24 voices, Misaki dictionary
Llama 3.2 1B
Llama 3.2 1B - Meta's lightweight mobile-optimized instruction-tuned LLM with 128K context
Ministral 3 3B
Ministral 3 3B Instruct - Mistral AI's edge-optimized instruction-tuned LLM with 256K context
Mistral 7B
Mistral 7B Instruct v0.3 - High-quality desktop LLM with function calling support
Phi4 Mini
Phi-4 Mini 3.8B - Microsoft's compact reasoning LLM with 128K context
Qwen2.5 0.5B Instruct
Qwen 2.5 0.5B Instruct - Small but capable instruction-tuned LLM from Alibaba Cloud
Smollm2 360M
SmolLM2 360M - HuggingFace's best tiny LLM, excellent quality/size ratio
Wav2vec2 Base 960H
Wav2Vec2 Base 960h - English ASR with CTC decoding
Whisper Tiny
Whisper Tiny - Fast multilingual ASR (Candle/SafeTensors runtime)