Open model run guides for named open-weight models, showing how to run each locally with Ollama, llama.cpp, vLLM, SGLang or MLX and what VRAM and context it needs.
Run Spark-X2.6-4B, an Apache 2.0 4B on-device agent model with 1M-token context, via Ollama, llama.cpp, LM Studio, MLX, vLLM or SGLang.
Run NVIDIA Dory1.0-4B locally with vLLM or llama.cpp on Apple Silicon, choose 1, 2 or 4 loops, and cut KV cache memory with last-loop caching.
DeepSeek-V4.1-Flash-1017 ships MIT-licensed with no Jinja template. See sampling settings, 1M context, the encoding folder and deepseek-recipe.
Learn how to pick, quantize, and run distilled models like DeepSeek-R1 locally with Ollama or llama.cpp, and when self-hosting beats API costs.
Learn how to run 671B MoE models like DeepSeek R1 locally with llama.cpp, KTransformers and Unsloth quants, with hardware tiers and tokens per second.
How to run the 320B-parameter GLM-5.3-Flash model on CPU with 128GB RAM using Unsloth's dynamic GGUF quants, plus the hardware math and exact commands.