Can I run Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 on an RTX 3060 12 GB?
No
Even its smallest file (Qwen3.8-27B-Coder390-EfficientThink-Q2LynnStyle-MTP, 13.3 GB) is more than an RTX 3060 12 GB can hold (10.8 GB usable): it needs 2 of them.
Files and context on RTX 3060 12 GB
Each file of Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 (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) |
|---|---|---|---|---|
| Q8_0 | 29.1 GB | Doesn't fit | — | — |
| Q6_K | 23.2 GB | Doesn't fit | — | — |
| Qwen3.8-27B-Coder390-EfficientThink-Q4LynnStyle-Q8MTP | 19.8 GB | Doesn't fit | — | — |
| Qwen3.8-27B-Coder390-EfficientThink-Q4LynnStyle-MTP | 19.6 GB | Doesn't fit | — | — |
| Qwen3.8-27B-Coder390-EfficientThink-Q3LynnStyle-Q8MTP | 17.5 GB | Doesn't fit | — | — |
| Qwen3.8-27B-Coder390-EfficientThink-Q3LynnStyle-MTP | 17.3 GB | Doesn't fit | — | — |
| Qwen3.8-27B-Coder390-EfficientThink-Q2LynnStyle-Q8MTP | 13.5 GB | Doesn't fit | — | — |
| Qwen3.8-27B-Coder390-Q3LynnStyle16G-MTP | 13.3 GB | Doesn't fit | — | — |
| Qwen3.8-27B-Coder390-EfficientThink-Q2LynnStyle-MTP | 13.3 GB | Doesn't fit | — | — |