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

Can I run ukisai_Swift-Qwen3.8-27b-GGUF on an NVIDIA B300?

Yes

Its BF16 file (54.7 GB) fits in the 259 GB an NVIDIA B300 can use, with room for ≈ 256K tokens of context.

Full analysis of ukisai_Swift-Qwen3.8-27b-GGUF Everything that runs on NVIDIA B300 Get the BF16 file on Hugging Face
llama-server -hf bartowski/ukisai_Swift-Qwen3.8-27b-GGUF:BF16

Files and context on NVIDIA B300

Each file of ukisai_Swift-Qwen3.8-27b-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 B300 Context (16-bit)Context (8-bit)
BF1654.7 GBFits256K256K
Q8_029.1 GBFits256K256K
Q6_K_L25.0 GBFits256K256K
Q6_K23.9 GBFits256K256K
Q6_K_S22.9 GBFits256K256K
Q5_K_M20.9 GBFits256K256K
Q5_K_S19.6 GBFits256K256K
Q4_K_L18.8 GBFits256K256K
Q4_117.8 GBFits256K256K
IQ4_NL17.4 GBFits256K256K
Q4_K_M17.4 GBFits256K256K
Q4_K_S16.4 GBFits256K256K
Q4_016.3 GBFits256K256K
IQ4_XS15.5 GBFits256K256K
IQ3_M14.9 GBFits256K256K
Q3_K_L14.1 GBFits256K256K
Q3_K_M13.4 GBFits256K256K
IQ3_XS12.8 GBFits256K256K
Q3_K_S12.7 GBFits256K256K
IQ3_XXS12.3 GBFits256K256K
Q2_K10.8 GBFits256K256K
IQ2_M10.5 GBFits256K256K
IQ2_S9.68 GBFits256K256K
IQ2_XS9.09 GBFits256K256K
IQ2_XXS8.88 GBFits256K256K

ukisai_Swift-Qwen3.8-27b-GGUF on other hardware

Popular models that run on NVIDIA B300

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.