Directory

AI Models

Browse 8 verified local AI models. Metadata only — all downloads go to original sources.

All chat coding instruct gguf low-ram 3b reasoning 7b creative multilingual fast image-gen
🤖
✓ Verified
Llama 3.1 8B Instruct
Meta's flagship 8B model from the Llama 3.1 series. Best overall performance in its class — handle…
💾 8.0GB RAM 📦 4.70GB Q4_K_M
🖥 Desktop
coding chat reasoning
⬇ 11,024
🤖
✓ Verified
Mistral 7B Instruct v0.3
One of the best 7B models available. Mistral 7B delivers outstanding instruction-following, coding a…
💾 6.0GB RAM 📦 4.10GB Q4_K_M
🖥 Desktop
coding chat reasoning
⬇ 9,341
🤖
✓ Verified
CodeLlama 7B Instruct
Meta's CodeLlama fine-tuned for instruction following in code contexts. Excellent at Python, JavaScr…
💾 6.0GB RAM 📦 3.80GB Q4_K_M
🖥 Desktop
coding instruct gguf
⬇ 7,263
🤖
✓ Verified
Phi-3 Mini 3.8B
Microsoft's Phi-3 Mini is remarkably capable for its parameter count. Optimized for reasoning and co…
💾 3.5GB RAM 📦 2.20GB Q4_K_M
📱 Mobile 🖥 Desktop
low-ram coding reasoning
⬇ 6,102
🤖
✓ Verified
Llama 3.2 3B Instruct
Meta's compact Llama 3.2 3B instruction-tuned model. Excellent performance for its size — handles …
💾 4.0GB RAM 📦 2.00GB Q4_K_M
📱 Mobile 🖥 Desktop
low-ram coding chat
⬇ 4,820
🤖
✓ Verified
Gemma 2 2B IT
Google's Gemma 2 2B instruction-tuned model. Ultra-light and surprisingly capable. Perfect for low-e…
💾 2.5GB RAM 📦 1.60GB Q4_0
📱 Mobile
low-ram chat gguf
⬇ 3,890
🤖
Qwen2.5 1.5B Instruct
Alibaba's Qwen2.5 1.5B — a surprisingly powerful tiny model with multilingual support including Ch…
💾 2.0GB RAM 📦 1.00GB Q4_0
📱 Mobile
low-ram chat multilingual
⬇ 2,140
🤖
TinyLlama 1.1B Chat
The smallest usable LLM. TinyLlama 1.1B Chat is ideal for very constrained devices — works on phon…
💾 1.5GB RAM 📦 0.70GB Q4_0
📱 Mobile
low-ram chat gguf
⬇ 1,893