Can I run Qwen3.6-35B-A3B-GGUF on an RTX 5060 Ti 16 GB?
Yes, just
Its UD-IQ3_S file (13.7 GB) fits in the 14.4 GB an RTX 5060 Ti 16 GB can use, with room for ≈ 31K tokens of context.
Full analysis of Qwen3.6-35B-A3B-GGUF
Everything that runs on RTX 5060 Ti 16 GB
Get the UD-IQ3_S file on Hugging Face
ollama run hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:UD-IQ3_SFiles and context on RTX 5060 Ti 16 GB
Each file of Qwen3.6-35B-A3B-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 5060 Ti 16 GB | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| BF16 | 69.4 GB | Doesn't fit | — | — |
| UD-Q8_K_XL | 38.5 GB | Doesn't fit | — | — |
| Q8_0 | 36.9 GB | Doesn't fit | — | — |
| UD-Q6_K_XL | 31.8 GB | Doesn't fit | — | — |
| UD-Q6_K | 29.3 GB | Doesn't fit | — | — |
| UD-Q5_K_XL | 26.6 GB | Doesn't fit | — | — |
| UD-Q5_K_M | 26.5 GB | Doesn't fit | — | — |
| UD-Q5_K_S | 24.9 GB | Doesn't fit | — | — |
| UD-Q4_K_XL | 22.4 GB | Doesn't fit | — | — |
| UD-Q4_K_M | 22.1 GB | Doesn't fit | — | — |
| MXFP4_MOE | 21.7 GB | Doesn't fit | — | — |
| UD-Q4_K_S | 20.9 GB | Doesn't fit | — | — |
| Qwen3.6-35B-A3B-UD-IQ4_NL_XL | 19.5 GB | Doesn't fit | — | — |
| UD-IQ4_NL | 18.0 GB | Doesn't fit | — | — |
| UD-IQ4_XS | 17.7 GB | Doesn't fit | — | — |
| UD-Q3_K_XL | 16.8 GB | Doesn't fit | — | — |
| UD-Q3_K_M | 16.6 GB | Doesn't fit | — | — |
| UD-Q3_K_S | 15.4 GB | Doesn't fit | — | — |
| UD-IQ3_S | 13.7 GB | Tight | 31K | 63K |
| UD-IQ3_XXS | 13.2 GB | Tight | 54K | 107K |
| UD-Q2_K_XL | 12.3 GB | Tight | 98K | 195K |
| UD-IQ2_M | 11.5 GB | Tight | 134K | 256K |
| UD-IQ2_XXS | 10.8 GB | Fits | 171K | 256K |
| UD-IQ1_M | 10.0 GB | Fits | 204K | 256K |