Model catalog
Browse 190 local AI models
190 local AI models across text, image, video and audio, each validated against vendor specs, HuggingFace and tool benchmarks (2026-11-01). Pick one to see its requirements and which of 49 devices can run it.
- Text LLMs
- 161
- All models
- 190
- Devices
- 49
Command
Command R
DeepSeek-R1
DeepSeek-R1-Distill
DeepSeek-V2
DeepSeek-V3
DeepSeek-V4
dots.llm
ERNIE
EXAONE
Falcon
Flint
Gemma
- →Gemma 3 270M0.27B · ? GB Q4
- →Gemma 3 1B1B · 0.81 GB Q4
- →Gemma 2 2B2.61B · 1.71 GB Q4
- →Gemma 3 4B4B · 2.49 GB Q4
- →Gemma 4 E2B5.1B · 3.11 GB Q4
- →Gemma 3n E4B8B · 4.23 GB Q4
- →Gemma 4 E4B8B · 4.98 GB Q4
- →Gemma 2 9B9B · 5.76 GB Q4
- →Gemma 3 12B12B · 7.3 GB Q4
- →Gemma 4 12B12B · 7.12 GB Q4
- →Gemma 4 26B-A4B26.5B MoE · 17.04 GB Q4
- →Gemma 2 27B27B · 16.65 GB Q4
- →Gemma 3 27B27B · 16.55 GB Q4
- →Gemma 4 31B32.7B · 18.32 GB Q4
GLM
gpt-oss
Granite
Hunyuan
Kimi
Laguna
LFM
- LF→LFM2 350M0.354B · 0.45 GB Q4
- LF→LFM2 700M0.742B · 0.92 GB Q4
- LF→LFM2 1.2B1.17B · 1.42 GB Q4
- LF→LFM2.5 1.2B1.17B · 0.73 GB Q4
- LF→LFM2.5 1.2B Thinking1.17B · 0.68 GB Q4
- LF→LFM3-1.7B1.73B · 1.02 GB Q4
- LF→LFM3-VL-2B1.92B · 1.38 GB Q4
- LF→LFM3 Omni 2B2.17B · 1.91 GB Q4
- LF→LFM2.5 8B-A1B8.3B MoE · 4.8 GB Q4
- LF→LFM2 24B-A2B24B MoE · 13.43 GB Q4
Llama
Llama 3.2 Vision
Llama 4
MiniCPM
MiniMax
Mistral
- →Ministral 3 3B3B · 2 GB Q4
- →Mistral 7B7B · 4.37 GB Q4
- →Ministral 3 8B8B · 4.84 GB Q4
- →Mistral Nemo 12B12.2B · 6.96 GB Q4
- →Ministral 3 14B14B · 7.67 GB Q4
- →Mistral Small 3 24B24B · 14.33 GB Q4
- →Mistral Small 3.1 24B24B · 13.35 GB Q4
- →Magistral Small24B · 14 GB Q4
- →Devstral Small24B · 13.35 GB Q4
- →Devstral Small 2 24B24B · 13.35 GB Q4
- →Mixtral 8x7B46.7B MoE · 26.49 GB Q4
- →Devstral 2 123B123B · 69.75 GB Q4
Muse
Nemotron
Nemotron 3
Nemotron 3.5
North
Olmo
OLMo
OpenELM
Ornith
phi
Phi-3.5
Phi-4
Qwen2.5
Qwen2.5-Coder
Qwen2.5-VL
Qwen3
Qwen3-Coder
Qwen3-VL
Qwen3.6
Qwen3.8
RNJ
Sarvam
Seed-OSS
SmolLM2
SmolLM3
TinyLlama
Yi
Image generation
- SD→Stable Diffusion 1.5860M UNET · ~3.7 GB at fp16
- SD→Stable Diffusion XL 1.02.6B UNET · ~7.5 GB at fp16
- SD→Stable Diffusion 3.5 Large8.1B MMDIT · ~7 GB at Q4 GGUF
- FX→FLUX.1 dev12B DIT · ~6.5 GB at Q4 GGUF
- FX→FLUX.1 schnell12B DIT · ~6.5 GB at Q4 GGUF
- →Qwen-Image20B MMDIT · ~14 GB at Q4_K_M GGUF
Video generation
- WA→Wan 2.1 T2V 1.3B1.3B DIT · ~6 GB at Q4 GGUF
- WA→Wan 2.1 T2V 14B14B DIT · ~12 GB at Q4 GGUF
- WA→Wan 2.2 TI2V 5B5B DIT · ~8 GB at Q4 GGUF
- WA→Wan 2.2 T2V A14B27B DIT · ~16 GB at Q4 GGUF
- LX→LTX-Video 2B2B DIT · ~10 GB at fp8 + offload
- LX→LTX-Video 13B13B DIT · ~20 GB at fp8
- CV→CogVideoX-5B5B DIT · ~16 GB at INT8 / fp8
- CV→CogVideoX-2B2B DIT · ~8 GB at fp16 + offload
- HY→HunyuanVideo13B DIT · ~16 GB at Q4 GGUF
- MO→Mochi 110B DIT · ~20 GB at fp8 + offload
- ST→Stable Video Diffusion (img2vid-XT)1.5B UNET · ~8 GB at fp16 + offload
Audio & voice
- →Whisper large-v3Speech to text · 1.55B · ~2.5 GB
- →Whisper large-v3-turboSpeech to text · 809M · ~1.5 GB
- →Whisper smallSpeech to text · 244M · ~0.85 GB
- KO→Kokoro-82MText to speech · 82M · ~1 GB
- OR→Orpheus 3BText to speech · 3B · ~4 GB
- BK→BarkText to speech (and sound effects) · 900M · ~5 GB
- DI→Dia 1.6BText to speech (dialogue) · 1.6B · ~10 GB
- →MusicGen smallMusic generation · 300M · ~3 GB
- →MusicGen mediumMusic generation · 1.5B · ~14 GB
- →MusicGen largeMusic generation · 3.3B · ~20 GB
- SA→Stable Audio Open 1.0Music and audio generation · 1.3B · ~15 GB
- LF→LFM3 Audio 2BSpeech recognition · 2B · ~4.61 GB
Browse by device
- Apple M1 (8GB)
- Apple M2 (16GB)
- Apple M3 Pro (18GB)
- Apple M4 (16GB)
- Apple M4 (24GB)
- Apple M4 Pro (24GB)
- Apple M4 Pro (48GB)
- Apple M4 Max (64GB)
- Apple M4 Max (128GB)
- Apple M3 Ultra (256GB)
- Nvidia GeForce RTX 3060 (12GB)
- Nvidia GeForce RTX 4060 Ti (16GB)
- Nvidia GeForce RTX 4070 (12GB)
- Nvidia GeForce RTX 4080 (16GB)
- Nvidia GeForce RTX 4090 (24GB)
- Nvidia GeForce RTX 5090 (32GB)
- Nvidia GeForce RTX 3090 (24GB)
- AMD Radeon RX 7900 XTX (24GB)
- AMD Ryzen AI Halo (128GB)
- 8GB RAM Laptop (CPU/iGPU only)
- 16GB RAM Laptop (CPU/iGPU only)
- 32GB RAM Laptop (CPU/iGPU only)
- iPhone 15 Pro
- iPhone 16
- iPhone 16 Pro
- iPad Pro M4 (16GB, 1TB/2TB config)
- Google Pixel 9 Pro
- Samsung Galaxy S24 Ultra
- Samsung Galaxy S25 Ultra (16GB, 1TB config only)
- Generic Android Phone (8GB RAM)
- Generic Android Phone (12GB RAM)
- Apple M5 (16GB)
- Apple M5 (32GB)
- Apple M5 Pro (48GB)
- Apple M5 Max (128GB)
- iPhone 17
- iPhone 17 Pro
- iPhone Air
- Google Pixel 10 Pro
- Samsung Galaxy S26 Ultra (16GB, 1TB config)
- Nvidia GeForce RTX 3060 Ti (8GB)
- Nvidia GeForce GTX 1070 (8GB)
- Nvidia GeForce RTX 2060 (6GB)
- Nvidia GeForce RTX 5080 (16GB)
- Nvidia GeForce RTX 5070 Ti (16GB)
- Nvidia GeForce RTX 5070 (12GB)
- Nvidia GeForce RTX 5060 Ti (16GB)
- AMD Radeon RX 9070 XT (16GB)
- Nvidia DGX Spark (128GB)
Or get a Rig Score for your exact machine.