Can I run gpt-neox-20b on an RTX 5090?
Probably, at 4-bit
The published weights are too big, but a 4-bit version (about 11.7 GB) would fit, with room for ≈ 2K tokens of context. The site hasn't analyzed a GGUF of gpt-neox-20b yet.
Files and context on RTX 5090
Each file of gpt-neox-20b (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.
| File | Size | On RTX 5090 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 41.3 GB | Doesn't fit | — | — |
| 4-bit (estimate) | 11.7 GB | Fits | 2K | 2K |