Model Anatomy See what's inside open-weight AI models

Can I run dolphin-2.9.1-yi-1.5-34b on an RTX 4090?

Probably, at 4-bit

The published weights are too big, but a 4-bit version (about 19.3 GB) would fit, with room for ≈ 8K tokens of context. The site hasn't analyzed a GGUF of dolphin-2.9.1-yi-1.5-34b yet.

Full analysis of dolphin-2.9.1-yi-1.5-34b Everything that runs on RTX 4090

Files and context on RTX 4090

Each file of dolphin-2.9.1-yi-1.5-34b (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

FileSizeOn RTX 4090 Context (16-bit)Context (8-bit)
As published68.8 GBDoesn't fit——
4-bit (estimate)19.3 GBTight8K8K

dolphin-2.9.1-yi-1.5-34b on other hardware

Popular models that run on RTX 4090

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.