Version

All recipes

Every validated recipe in one table: model, size, architecture, precision, and the verified hardware. Select a row for the full recipe.

Model	Size	Arch	Precision	Verified on	Notes
Qwen3-8B qwen	8B	Dense	BF16	EKS L4	An 8.2B dense chat model on a single NVIDIA L4.
Qwen3-Coder-480B qwen	480B A35B	MoE	BF16 / FP8	EKS H200	A 480B code MoE, multi-node BF16 over EFA or single-node FP8 on SGLang.
Kimi-K2 moonshotai	1T A32B	MoE	INT4	EKS H200	A 1T MoE served prefill/decode disaggregated across two H200 nodes.
Llama-3.1-8B meta-llama	8B	Dense	BF16	EKSGKE L4	An 8B dense chat model on a single NVIDIA L4.
GLM-4.5-Air zai-org	106B A12B	MoE	GGUF IQ4_XS	GKE A100	A 106B MoE served from a GGUF checkpoint via llama.cpp on a single A100.
Nemotron-3.5-Lightning nvidia	30B A3B	MoE	NVFP4	Nebius H100	An open 30B MoE with 3B active parameters served NVFP4 on a single H100 on Nebius.