Can I run Qwen3.8-27B-GSQ-RCO-GGUF on an RTX 3060 12 GB?
Yes, just
Its Qwen3.8-27B-GSQ-RCO-IQ3_XXS file (10.1 GB) fits in the 10.8 GB an RTX 3060 12 GB can use, with room for ≈ 8K tokens of context.
Full analysis of Qwen3.8-27B-GSQ-RCO-GGUF
Everything that runs on RTX 3060 12 GB
Get the Qwen3.8-27B-GSQ-RCO-IQ3_XXS file on Hugging Face
ollama run hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUFFiles and context on RTX 3060 12 GB
Each file of Qwen3.8-27B-GSQ-RCO-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) |
|---|---|---|---|---|
| IQ3_S | 12.1 GB | Doesn't fit | — | — |
| Qwen3.8-27B-GSQ-RCO-IQ3_S | 11.8 GB | Doesn't fit | — | — |
| IQ3_XXS | 10.4 GB | Doesn't fit | 3K | 6K |
| Qwen3.8-27B-GSQ-RCO-IQ3_XXS | 10.1 GB | Tight | 8K | 16K |
| IQ2_S | 9.61 GB | Tight | 15K | 31K |
| Qwen3.8-27B-GSQ-RCO-IQ2_S | 9.26 GB | Tight | 21K | 41K |
| IQ2_XS | 8.77 GB | Tight | 28K | 56K |
| Qwen3.8-27B-GSQ-RCO-IQ2_XS | 8.42 GB | Fits | 33K | 66K |