Can I run NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF on an RTX 3060 12 GB?
Yes
Its UD-Q8_K_XL file (8.19 GB) fits in the 10.8 GB an RTX 3060 12 GB can use, with room for ≈ 86K tokens of context.
Full analysis of NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF
Everything that runs on RTX 3060 12 GB
Get the UD-Q8_K_XL file on Hugging Face
ollama run hf.co/unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:UD-Q8_K_XLFiles and context on RTX 3060 12 GB
Each file of NVIDIA-Nemotron-3.5-Bolt-E4B-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) |
|---|---|---|---|---|
| BF16 | 15.1 GB | Doesn't fit | — | — |
| UD-Q8_K_XL | 8.19 GB | Fits | 86K | 128K |
| UD-Q6_K_XL | 7.26 GB | Fits | 118K | 128K |
| UD-Q5_K_XL | 5.83 GB | Fits | 128K | 128K |
| UD-Q4_K_XL | 5.06 GB | Fits | 128K | 128K |
| UD-Q3_K_XL | 4.22 GB | Fits | 128K | 128K |
| UD-Q2_K_XL | 3.74 GB | Fits | 128K | 128K |
| UD-IQ3_XXS | 3.70 GB | Fits | 128K | 128K |
| UD-IQ2_M | 3.53 GB | Fits | 128K | 128K |