Browse GPUs and AI apps

DeepSeek-R1-0528 reasoning distilled into Qwen3 8B, on llama.cpp.

• Qwen 1.5B
• Qwen 7B
• 0528 Qwen3 8B
• Llama 8B
• Qwen 14B
• Qwen 32B

Mistral's coding agent model, 4-bit GGUF on llama.cpp.

Google's Gemma 3 12B, 4-bit GGUF, on llama.cpp; fits 12 GB cards; runs on NVIDIA, AMD, Intel Arc and Apple silicon.

• 270M
• 1B
• 4B
• 12B
• 27B

Google's on-device Gemma 3n, 8-bit GGUF on llama.cpp.

Google's Gemma 4 12B, 4-bit GGUF on llama.cpp.

• E4B
• 12B
• 26B A4B
• 31B

OpenAI's open-weight 120B reasoning model on llama.cpp.

Meta's Llama 3.1 8B Instruct, 4-bit GGUF on llama.cpp.

Meta's Llama 3.2 1B, a small chat model on llama.cpp.

• 1B
• 3B

Meta's Llama 3.3 70B, 4-bit GGUF, on llama.cpp; one 48 GB card runs it; runs on NVIDIA, AMD, Intel Arc and Apple silicon.

Mistral's reasoning model, 4-bit GGUF on llama.cpp.

Mistral 7B Instruct v0.3, 4-bit GGUF on llama.cpp.

Mistral Nemo 12B Instruct, 4-bit GGUF on llama.cpp.

Mistral Small 3.2 (24B), 4-bit GGUF with a 16K context, on llama.cpp; fits 24 GB cards; runs on NVIDIA, AMD, Intel Arc and Apple silicon.

Text embeddings for search and RAG on llama.cpp.

Ollama daemon; pull models on demand and call its API through an SSH tunnel; the same template runs on NVIDIA (CUDA) and AMD (ROCm) GPUs.

Microsoft's Phi-4 14B, 4-bit GGUF on llama.cpp.

Microsoft's Phi-4 mini, a small chat model on llama.cpp.

Qwen2.5 Coder 14B for code completion and chat on llama.cpp.

• 7B
• 14B
• 32B

The smallest Qwen3, for tests and light chat on llama.cpp.

• 0.6B
• 1.7B
• 4B
• 8B · vLLM
• 8B · llama.cpp
• 14B
• 30B A3B
• 32B

Qwen3 Coder for editors and agents, 4-bit GGUF on llama.cpp.

Qwen3 text embeddings for search and RAG on llama.cpp.

Hugging Face's SmolLM3 3B, 4-bit GGUF on llama.cpp.