Can I run Qwen3.8-27B-pi-GGUF on an RTX 3090?
Yes, just
Its Q5_K_M file (19.2 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 33K tokens of context.
Full analysis of Qwen3.8-27B-pi-GGUF
Everything that runs on RTX 3090
Get the Q5_K_M file on Hugging Face
ollama run hf.co/bytkim/Qwen3.8-27B-pi-GGUF:Q5_K_MFiles and context on RTX 3090
Each file of Qwen3.8-27B-pi-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) |
|---|---|---|---|---|
| BF16 | 53.8 GB | Doesn't fit | — | — |
| Q8_0 | 28.6 GB | Doesn't fit | — | — |
| Q6_K | 22.1 GB | Doesn't fit | — | — |
| Q5_K_M | 19.2 GB | Tight | 33K | 66K |
| Q5_K_S | 18.7 GB | Tight | 41K | 82K |
| Q4_K_M | 16.5 GB | Fits | 73K | 146K |
| IQ4_NL | 15.8 GB | Fits | 84K | 168K |
| Q4_K_S | 15.6 GB | Fits | 87K | 175K |
| IQ4_XS | 15.1 GB | Fits | 95K | 190K |
| Q3_K_L | 14.3 GB | Fits | 106K | 212K |
| Q3_K_M | 13.3 GB | Fits | 121K | 243K |
| IQ3_M | 12.6 GB | Fits | 132K | 256K |
| Q3_K_S | 12.1 GB | Fits | 140K | 256K |
| IQ3_XS | 12.0 GB | Fits | 141K | 256K |
| Q2_K | 10.7 GB | Fits | 160K | 256K |
| IQ2_M | 10.0 GB | Fits | 170K | 256K |
| IQ2_S | 9.36 GB | Fits | 180K | 256K |
| IQ2_XS | 9.09 GB | Fits | 184K | 256K |