vLLM Recipes — Deploy any model on any hardware with vLLM
Pick a model, adjust for your GPUs, copy the vllm serve line that runs. Community-maintained recipes for VASTAI Tech VA16 VA10L VA1L. Full vLLM compatibility →
Qwen3-0.6B
Qwen
0.6Bbf1633K ctxtext
Qwen3-0.6B is a large language model with 0.6B parameters, capable of performing text-to-text generation with a wide range of tasks. The model is trained on a large amount of data, and is capable of handling long-form inputs.
DeepSeek-V3
deepseek-ai
671B/37Bfp8131K ctxtext
DeepSeek-V3 is a 671B-parameter MoE model with 37B active parameters, supporting up to 128K context length
Browse by provider