Can I run Cyber-Tiel-Coder-35B-A3B-GGUF-MTP on an NVIDIA B300?

Yes

Its UD-Q8_K_XL file (38.8 GB) fits in the 259 GB an NVIDIA B300 can use, with room for ≈ 256K tokens of context.

Full analysis of Cyber-Tiel-Coder-35B-A3B-GGUF-MTP Everything that runs on NVIDIA B300 Get the UD-Q8_K_XL file on Hugging Face

ollama run hf.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP:UD-Q8_K_XL

Files and context on NVIDIA B300

Each file of Cyber-Tiel-Coder-35B-A3B-GGUF-MTP (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.

File	Size	On NVIDIA B300	Context (16-bit)	Context (8-bit)
UD-Q8_K_XL	38.8 GB	Fits	256K	256K
UD-Q6_K_XL	32.2 GB	Fits	256K	256K
UD-Q5_K_XL	27.0 GB	Fits	256K	256K
UD-Q5_K_S	25.3 GB	Fits	256K	256K
UD-Q4_K_XL	22.7 GB	Fits	256K	256K
UD-Q4_K_M	22.5 GB	Fits	256K	256K
UD-Q4_K_S	21.3 GB	Fits	256K	256K
UD-IQ4_XS	18.1 GB	Fits	256K	256K
UD-Q3_K_XL	17.2 GB	Fits	256K	256K
UD-IQ3_S	14.1 GB	Fits	256K	256K
UD-IQ3_XXS	13.6 GB	Fits	256K	256K
UD-Q2_K_XL	12.7 GB	Fits	256K	256K

Cyber-Tiel-Coder-35B-A3B-GGUF-MTP 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.