Can I run Swift-Qwen3.8-27B-GGUF on an RTX 3060 12 GB?
Yes, just
Its IQ2_S file (9.90 GB) fits in the 10.8 GB an RTX 3060 12 GB can use, with room for ≈ 11K tokens of context. That file is under 3 bits per weight, so expect noticeably lower quality.
Full analysis of Swift-Qwen3.8-27B-GGUF
Everything that runs on RTX 3060 12 GB
Get the IQ2_S file on Hugging Face
ollama run hf.co/ukisai/Swift-Qwen3.8-27B-GGUF:IQ2_SFiles and context on RTX 3060 12 GB
Each file of Swift-Qwen3.8-27B-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 3060 12 GB | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| F16 | 54.7 GB | Doesn't fit | — | — |
| Q8_0 | 29.1 GB | Doesn't fit | — | — |
| Q6_K_L | 25.2 GB | Doesn't fit | — | — |
| Q6_K_S | 23.1 GB | Doesn't fit | — | — |
| Q6_K | 22.9 GB | Doesn't fit | — | — |
| Q5_K_M | 20.2 GB | Doesn't fit | — | — |
| Q5_K_S | 19.8 GB | Doesn't fit | — | — |
| Q4_K_L | 19.0 GB | Doesn't fit | — | — |
| Q4_K_M | 18.0 GB | Doesn't fit | — | — |
| IQ4_NL | 17.7 GB | Doesn't fit | — | — |
| Q4_1 | 17.5 GB | Doesn't fit | — | — |
| Q4_K_S | 16.6 GB | Doesn't fit | — | — |
| Q4_0 | 16.0 GB | Doesn't fit | — | — |
| IQ4_XS | 15.7 GB | Doesn't fit | — | — |
| IQ3_M | 15.1 GB | Doesn't fit | — | — |
| Q3_K_L | 14.3 GB | Doesn't fit | — | — |
| Q3_K_M | 13.6 GB | Doesn't fit | — | — |
| IQ3_XS | 13.0 GB | Doesn't fit | — | — |
| Q3_K_S | 13.0 GB | Doesn't fit | — | — |
| IQ3_XXS | 12.5 GB | Doesn't fit | — | — |
| Q2_K | 11.0 GB | Doesn't fit | — | — |
| IQ2_M | 10.7 GB | Doesn't fit | — | — |
| IQ2_S | 9.90 GB | Tight | 11K | 22K |
| IQ2_XS | 9.30 GB | Tight | 20K | 40K |
| IQ2_XXS | 9.09 GB | Tight | 23K | 46K |