Can I run Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF on an RTX 3090?
Yes, just
Its Q5_K_M file (19.5 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 28K tokens of context.
Full analysis of Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF
Everything that runs on RTX 3090
Get the Q5_K_M file on Hugging Face
ollama run hf.co/DavidAU/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF:Q5_K_MFiles and context on RTX 3090
Each file of Qwen3.8-27B-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 RTX 3090 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| Q8_0 | 29.0 GB | Doesn't fit | — | — |
| Qwen3.8-27B-Ultimate-Heretic-Uncn-Turbo-Brilli-50x-AGI-NEO-Q8_0 | 28.6 GB | Doesn't fit | — | — |
| Q6_K | 22.4 GB | Doesn't fit | — | — |
| Qwen3.8-27B-Ultimate-Heretic-Uncn-Turbo-Brilli-50x-AGI-NEO-Q6_K | 22.1 GB | Doesn't fit | — | — |
| Q5_K_M | 19.5 GB | Tight | 28K | 57K |
| Q5_K_S | 19.0 GB | Tight | 37K | 74K |
| Q4_K_M | 16.8 GB | Fits | 69K | 138K |
| IQ4_NL | 16.0 GB | Fits | 81K | 161K |
| Q4_K_S | 15.8 GB | Fits | 84K | 168K |
| Qwen3.8-27B-Ultimate-Heretic-Uncn-Turbo-Brilli-50x-AGI-NEO-MTP-IQ4_XS | 15.3 GB | Fits | 91K | 183K |
| IQ4_XS | 15.1 GB | Fits | 95K | 190K |
| IQ3_M | 12.8 GB | Fits | 129K | 256K |
| IQ2_M | 10.2 GB | Fits | 167K | 256K |