Can I run NeoHorse-1-4B-GGUF on a Radeon RX 9070 XT?
Yes
Its BF16 file (8.42 GB) fits in the 14.4 GB a Radeon RX 9070 XT can use, with room for ≈ 177K tokens of context.
Full analysis of NeoHorse-1-4B-GGUF
Everything that runs on Radeon RX 9070 XT
Get the BF16 file on Hugging Face
ollama run hf.co/TokenRhythm/NeoHorse-1-4B-GGUF:BF16Files and context on Radeon RX 9070 XT
Each file of NeoHorse-1-4B-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.