Deploy Open Models on GPUs

Choose a GPU setup and a capability to find the best open models that fit, and deploy one as an API.

Coding · 2× NVIDIA RTX 5090

Ranked by benchmark scores for Code generation, completion and repair

#	Model	Params	Precision	Max context	Score (0–10)	(0–10)
1	Kimi-VL-A3B-Thinking-2506 2025.06	16.4B	FP16	128K	4.20

Deployment verified on HyperAI

Scores aggregate public benchmarks for the selected capability.
Fits usable VRAM with weights plus KV cache at 64K+ context, at the best precision.