Can I run Ripple-65B-Preview-GGUF on a Radeon RX 7900 XTX?
Yes, just
Its IQ2_XXS file (20.0 GB) fits in the 21.6 GB a Radeon RX 7900 XTX can use, with room for ≈ 20K tokens of context. That file is under 3 bits per weight, so expect noticeably lower quality.
Full analysis of Ripple-65B-Preview-GGUF
Everything that runs on Radeon RX 7900 XTX
Get the IQ2_XXS file on Hugging Face
ollama run hf.co/AtomicChat/Ripple-65B-Preview-GGUF:IQ2_XXSFiles and context on Radeon RX 7900 XTX
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 Radeon RX 7900 XTX | 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 | Doesn't fit | — | — |
| Ripple-65B-Preview-Q4_K_M | 38.8 GB | Doesn't fit | — | — |
| IQ4_XS | 38.7 GB | Doesn't fit | — | — |
| IQ3_S | 32.4 GB | Doesn't fit | — | — |
| IQ3_XXS | 28.0 GB | Doesn't fit | — | — |
| IQ2_S | 25.3 GB | Doesn't fit | — | — |
| IQ2_XS | 22.1 GB | Doesn't fit | — | — |
| IQ2_XXS | 20.0 GB | Tight | 20K | 43K |
| IQ1_M | 18.5 GB | Tight | 42K | 89K |