Can I run Qwen3.6-27B-GGUF on an RTX 5080?
Yes, just
Its Q3_K_M file (13.6 GB) fits in the 14.4 GB an RTX 5080 can use, with room for ≈ 10K tokens of context.
Full analysis of Qwen3.6-27B-GGUF
Everything that runs on RTX 5080
Get the Q3_K_M file on Hugging Face
ollama run hf.co/unsloth/Qwen3.6-27B-GGUF:Q3_K_MFiles and context on RTX 5080
Each file of Qwen3.6-27B-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 5080 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| BF16 | 53.8 GB | Doesn't fit | — | — |
| UD-Q8_K_XL | 35.3 GB | Doesn't fit | — | — |
| Q8_0 | 28.6 GB | Doesn't fit | — | — |
| UD-Q6_K_XL | 25.6 GB | Doesn't fit | — | — |
| Q6_K | 22.5 GB | Doesn't fit | — | — |
| UD-Q5_K_XL | 20.0 GB | Doesn't fit | — | — |
| Q5_K_M | 19.5 GB | Doesn't fit | — | — |
| Q5_K_S | 19.0 GB | Doesn't fit | — | — |
| UD-Q4_K_XL | 17.6 GB | Doesn't fit | — | — |
| Q4_1 | 17.3 GB | Doesn't fit | — | — |
| Q4_K_M | 16.8 GB | Doesn't fit | — | — |
| IQ4_NL | 16.1 GB | Doesn't fit | — | — |
| Q4_K_S | 15.9 GB | Doesn't fit | — | — |
| Q4_0 | 15.8 GB | Doesn't fit | — | — |
| IQ4_XS | 15.4 GB | Doesn't fit | — | — |
| UD-Q3_K_XL | 14.5 GB | Doesn't fit | — | — |
| Q3_K_M | 13.6 GB | Tight | 10K | 20K |
| Q3_K_S | 12.4 GB | Tight | 28K | 56K |
| UD-IQ3_XXS | 12.0 GB | Tight | 34K | 67K |
| UD-Q2_K_XL | 11.8 GB | Tight | 36K | 71K |
| UD-IQ2_M | 10.8 GB | Fits | 51K | 101K |
| UD-IQ2_XXS | 9.39 GB | Fits | 72K | 145K |