Inference configs for local LLMs
Ready-to-run settings to run a model on your own machine: Ollama Modelfile, vLLM command, llama.cpp.
contextetech
Mistral 7B on a 16 GB Mac with Ollama
Ollama Modelfile to run Mistral 7B Instruct locally on a 16 GB Mac: Q4…
contextetech
Qwen2.5 7B with vLLM on a 24 GB GPU
Serve Qwen2.5 7B Instruct with vLLM on a 24 GB GPU: OpenAI-compatible API, 8k…
contextetech
llama.cpp server for a GGUF model
Run any GGUF model with the llama.cpp server: OpenAI-compatible API on port…
What is an inference config?
An inference config is the set of settings needed to run a model on your own machine: the runtime (Ollama, vLLM, llama.cpp), quantization, context size and launch command.
Guide: Inference configs →