Model Anatomy See what's inside open-weight AI models

Can I run Qwen3.8-35B-A3B-Distill-GGUF on an RTX 5080?

Yes, just

Its Q2_K file (13.8 GB) fits in the 14.4 GB an RTX 5080 can use, 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-GGUF Everything that runs on RTX 5080 Get the Q2_K file on Hugging Face
ollama run hf.co/empero-ai/Qwen3.8-35B-A3B-Distill-GGUF:Q2_K

Files and context on RTX 5080

Each file of Qwen3.8-35B-A3B-Distill-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.

FileSizeOn RTX 5080 Context (16-bit)Context (8-bit)
BF1671.1 GBDoesn't fit——
Q8_037.8 GBDoesn't fit——
Q6_K29.2 GBDoesn't fit——
Q5_K_M25.3 GBDoesn't fit——
Q4_K_M21.7 GBDoesn't fit——
IQ4_XS19.6 GBDoesn't fit——
Q3_K_M17.7 GBDoesn't fit——
IQ3_M16.3 GBDoesn't fit——
Q2_K13.8 GBTight24K47K
IQ2_M12.6 GBTight85K170K

Qwen3.8-35B-A3B-Distill-GGUF on other hardware

Popular models that run on RTX 5080

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.