Can I run Qwen3.8-40B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF on a Radeon RX 7900 XTX?
Yes, just
Its IQ3_M file (18.3 GB) fits in the 21.6 GB a Radeon RX 7900 XTX can use, with room for ≈ 30K tokens of context.
Full analysis of Qwen3.8-40B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF
Everything that runs on Radeon RX 7900 XTX
Get the IQ3_M file on Hugging Face
ollama run hf.co/DavidAU/Qwen3.8-40B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF:IQ3_MFiles and context on Radeon RX 7900 XTX
Each file of Qwen3.8-40B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-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) |
|---|---|---|---|---|
| Q8_0 | 42.0 GB | Doesn't fit | — | — |
| Q6_K | 32.4 GB | Doesn't fit | — | — |
| Q5_K_M | 28.2 GB | Doesn't fit | — | — |
| Q5_K_S | 27.3 GB | Doesn't fit | — | — |
| Q4_K_M | 24.2 GB | Doesn't fit | — | — |
| Q4_K_S | 22.7 GB | Doesn't fit | — | — |
| Qwen3.8-40B-Ultimate-Heretic-Uncn-Turbo-Brilli-50x-AGI-NEO-MTP-IQ4_XS | 22.0 GB | Doesn't fit | — | — |
| IQ4_XS | 21.8 GB | Doesn't fit | — | — |
| IQ3_M | 18.3 GB | Tight | 30K | 61K |
| IQ2_M | 14.5 GB | Fits | 68K | 136K |