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

Can I run Dolphin3-Cyber-8B-GGUF on an NVIDIA B300?

Yes

Its F16 file (16.1 GB) fits in the 259 GB an NVIDIA B300 can use, with room for ≈ 128K tokens of context.

Full analysis of Dolphin3-Cyber-8B-GGUF Everything that runs on NVIDIA B300 Get the F16 file on Hugging Face
ollama run hf.co/RavichandranJ/Dolphin3-Cyber-8B-GGUF:F16

Files and context on NVIDIA B300

Each file of Dolphin3-Cyber-8B-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)
F1616.1 GBFits128K128K
Q8_08.54 GBFits128K128K
Q6_K6.60 GBFits128K128K
Q5_K_M5.73 GBFits128K128K
Q5_05.60 GBFits128K128K
Q5_K_S5.60 GBFits128K128K
Q4_K_M4.92 GBFits128K128K
Q4_K_S4.69 GBFits128K128K
Q4_04.66 GBFits128K128K
Q3_K_M4.02 GBFits128K128K
Q2_K3.18 GBFits128K128K

Dolphin3-Cyber-8B-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.