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

Can I run Swift-1.5-Qwen3.8-27B-heretic-GSQ-RCO-GGUF on an NVIDIA B200?

Yes

Its IQ3_S file (12.1 GB) fits in the 162 GB an NVIDIA B200 can use, with room for ≈ 256K tokens of context.

Full analysis of Swift-1.5-Qwen3.8-27B-heretic-GSQ-RCO-GGUF Everything that runs on NVIDIA B200 Get the IQ3_S file on Hugging Face
ollama run hf.co/jegreene/Swift-1.5-Qwen3.8-27B-heretic-GSQ-RCO-GGUF:IQ3_S

Files and context on NVIDIA B200

Each file of Swift-1.5-Qwen3.8-27B-heretic-GSQ-RCO-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 NVIDIA B200 Context (16-bit)Context (8-bit)
IQ3_S12.1 GBFits256K256K
IQ3_XXS10.4 GBFits256K256K
IQ2_S9.61 GBFits256K256K

Swift-1.5-Qwen3.8-27B-heretic-GSQ-RCO-GGUF on other hardware

Popular models that run on NVIDIA B200

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.