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

Can I run Qwen3.8-3.6-27B-blend on an RTX 6000 Ada?

Yes, with a GGUF version

The published weights are too big, but the Q5_K_M file from JetBrains/Qwen3.8-3.6-27B-blend-GGUF (19.5 GB) fits, with room for ≈ 256K tokens of context.

Full analysis of Qwen3.8-3.6-27B-blend Everything that runs on RTX 6000 Ada Get the Q5_K_M file on Hugging Face
ollama run hf.co/JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q5_K_M

Files and context on RTX 6000 Ada

Each file of Qwen3.8-3.6-27B-blend (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 6000 Ada Context (16-bit)Context (8-bit)
As published55.6 GBDoesn't fit——
Q5_K_MJetBrains/Qwen3.8-3.6-27B-blend-GGUF19.5 GBFits256K256K
Q4_K_MJetBrains/Qwen3.8-3.6-27B-blend-GGUF16.8 GBFits256K256K
IQ4_XSJetBrains/Qwen3.8-3.6-27B-blend-GGUF14.3 GBFits256K256K
Q3_K_XLJetBrains/Qwen3.8-3.6-27B-blend-GGUF13.1 GBFits256K256K
IQ3_SJetBrains/Qwen3.8-3.6-27B-blend-GGUF12.6 GBFits256K256K

Qwen3.8-3.6-27B-blend on other hardware

Popular models that run on RTX 6000 Ada

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.