Can I run Qwen3.8-35B-A3B-Distill on an RTX 5060 Ti 16 GB?
Yes, with a GGUF version
The published weights are too big, but the Q2_K file from empero-ai/Qwen3.8-35B-A3B-Distill-GGUF (13.8 GB) fits, with room for ≈ 24K tokens of context. That file is under 3 bits per weight, so expect noticeably lower quality.
Full analysis of Qwen3.8-35B-A3B-Distill
Everything that runs on RTX 5060 Ti 16 GB
Get the Q2_K file on Hugging Face
ollama run hf.co/empero-ai/Qwen3.8-35B-A3B-Distill-GGUF:Q2_KFiles and context on RTX 5060 Ti 16 GB
Each file of Qwen3.8-35B-A3B-Distill (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) |
|---|---|---|---|---|
| As published | 71.9 GB | Doesn't fit | — | — |
| BF16 | 71.1 GB | Doesn't fit | — | — |
| Q8_0 | 37.8 GB | Doesn't fit | — | — |
| Q6_K | 29.2 GB | Doesn't fit | — | — |
| Q5_K_M | 25.3 GB | Doesn't fit | — | — |
| Q4_K_M | 21.7 GB | Doesn't fit | — | — |
| IQ4_XS | 19.6 GB | Doesn't fit | — | — |
| Q3_K_M | 17.7 GB | Doesn't fit | — | — |
| IQ3_M | 16.3 GB | Doesn't fit | — | — |
| Q2_K | 13.8 GB | Tight | 24K | 47K |
| IQ2_M | 12.6 GB | Tight | 85K | 170K |