Can I run Nanbeige4.3-33B-GGUF on an RTX 4090?
Yes, just
Its IQ4_XS file (20.3 GB) fits in the 21.6 GB an RTX 4090 can use, with room for ≈ 6K tokens of context.
Full analysis of Nanbeige4.3-33B-GGUF
Everything that runs on RTX 4090
Get the IQ4_XS file on Hugging Face
ollama run hf.co/AtomicChat/Nanbeige4.3-33B-GGUF:IQ4_XSFiles and context on RTX 4090
Each file of Nanbeige4.3-33B-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.
| File | Size | On RTX 4090 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| Q8_0 | 35.2 GB | Doesn't fit | — | — |
| Q6_K | 30.1 GB | Doesn't fit | — | — |
| Q5_K | 27.9 GB | Doesn't fit | — | — |
| Q5_K_M | 24.7 GB | Doesn't fit | — | — |
| Nanbeige4.3-33B-Q5_K_M | 23.5 GB | Doesn't fit | — | — |
| Nanbeige4.3-33B-AD-Q5_K_M-Q4_K_M | 22.6 GB | Doesn't fit | — | — |
| Q4_K_M | 21.2 GB | Doesn't fit | 2K | 4K |
| IQ4_XS | 20.3 GB | Tight | 6K | 11K |
| IQ3_S | 17.1 GB | Fits | 21K | 42K |
| IQ3_XXS | 14.9 GB | Fits | 31K | 61K |
| IQ2_S | 13.7 GB | Fits | 36K | 72K |