Can I run Tiel-Coder-35B-A3B-GGUF on an NVIDIA H100?

Yes

Its UD-Q8_K_XL file (38.5 GB) fits in the 72.0 GB an NVIDIA H100 can use, with room for ≈ 256K tokens of context.

Full analysis of Tiel-Coder-35B-A3B-GGUF Everything that runs on NVIDIA H100 Get the UD-Q8_K_XL file on Hugging Face

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

Files and context on NVIDIA H100

Each file of Tiel-Coder-35B-A3B-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.

File	Size	On NVIDIA H100	Context (16-bit)	Context (8-bit)
UD-Q8_K_XL	38.5 GB	Fits	256K	256K
UD-Q6_K_XL	31.8 GB	Fits	256K	256K
UD-Q5_K_XL	26.6 GB	Fits	256K	256K
UD-Q4_K_XL	22.4 GB	Fits	256K	256K
UD-Q4_K_S	20.9 GB	Fits	256K	256K
UD-IQ4_XS	17.7 GB	Fits	256K	256K
UD-Q3_K_XL	16.8 GB	Fits	256K	256K
UD-IQ3_XXS	13.2 GB	Fits	256K	256K
UD-Q2_K_XL	12.3 GB	Fits	256K	256K

Tiel-Coder-35B-A3B-GGUF on other hardware

Popular models that run on NVIDIA H100

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.