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

Can I run Ornith-1.5-35B-A3B on an RTX 4090?

Probably, at 4-bit

The published weights are too big, but a 4-bit version (about 20.2 GB) would fit, with room for ≈ 63K tokens of context. The site hasn't analyzed a GGUF of Ornith-1.5-35B-A3B yet.

Full analysis of Ornith-1.5-35B-A3B Everything that runs on RTX 4090

Files and context on RTX 4090

Each file of Ornith-1.5-35B-A3B (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 published71.9 GBDoesn't fit——
BF16ornith-ai/Ornith-1.5-35B-A3B-GGUF71.1 GBDoesn't fit——
Q8_0ornith-ai/Ornith-1.5-35B-A3B-GGUF37.8 GBDoesn't fit——
Q6_Kornith-ai/Ornith-1.5-35B-A3B-GGUF29.2 GBDoesn't fit——
Q5_K_Mornith-ai/Ornith-1.5-35B-A3B-GGUF25.3 GBDoesn't fit——
Q4_K_Mornith-ai/Ornith-1.5-35B-A3B-GGUF21.7 GBDoesn't fit——

Ornith-1.5-35B-A3B 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.