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

Can I run Signal-3.8-27B-GGUF on a Radeon RX 9070 XT?

Yes, just

Its IQ3_S file (13.3 GB) fits in the 14.4 GB a Radeon RX 9070 XT can use, with room for ≈ 14K tokens of context.

Full analysis of Signal-3.8-27B-GGUF Everything that runs on Radeon RX 9070 XT Get the IQ3_S file on Hugging Face
ollama run hf.co/agentionai/Signal-3.8-27B-GGUF:IQ3_S

Files and context on Radeon RX 9070 XT

Each file of Signal-3.8-27B-GGUF (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 Radeon RX 9070 XT Context (16-bit)Context (8-bit)
Q8_029.0 GBDoesn't fit——
Q6_K22.4 GBDoesn't fit——
Q5_K_M19.5 GBDoesn't fit——
Q4_K_XL17.6 GBDoesn't fit——
Q4_K_M17.0 GBDoesn't fit——
Q3_K_XL15.1 GBDoesn't fit——
IQ4_XS14.3 GBDoesn't fit——
IQ3_S13.3 GBTight14K28K
IQ3_XXS12.2 GBTight30K60K

Signal-3.8-27B-GGUF on other hardware

Popular models that run on Radeon RX 9070 XT

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.