Can I run Ripple-65B-Preview-GGUF on an RTX 6000 Ada?
Yes, just
Its Q4_K_M file (40.4 GB) fits in the 43.2 GB an RTX 6000 Ada can use, with room for ≈ 37K tokens of context.
Full analysis of Ripple-65B-Preview-GGUF
Everything that runs on RTX 6000 Ada
Get the Q4_K_M file on Hugging Face
ollama run hf.co/AtomicChat/Ripple-65B-Preview-GGUF:Q4_K_MFiles and context on RTX 6000 Ada
Each file of Ripple-65B-Preview-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 6000 Ada | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| BF16 | 130 GB | Doesn't fit | — | — |
| Q8_0 | 68.8 GB | Doesn't fit | — | — |
| Q6_K | 57.7 GB | Doesn't fit | — | — |
| Q5_K_M | 47.9 GB | Doesn't fit | — | — |
| Q4_K_M | 40.4 GB | Tight | 37K | 79K |
| Ripple-65B-Preview-Q4_K_M | 38.8 GB | Tight | 62K | 127K |
| IQ4_XS | 38.7 GB | Tight | 63K | 129K |
| IQ3_S | 32.4 GB | Fits | 157K | 318K |
| IQ3_XXS | 28.0 GB | Fits | 223K | 450K |
| IQ2_S | 25.3 GB | Fits | 263K | 529K |
| IQ2_XS | 22.1 GB | Fits | 310K | 624K |
| IQ2_XXS | 20.0 GB | Fits | 342K | 687K |
| IQ1_M | 18.5 GB | Fits | 364K | 732K |