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

Can I run Qwen3-Next-80B-A3B-Thinking-GGUF on an NVIDIA H100?

Yes, just

Its Q6_K file (65.5 GB) fits in the 72.0 GB an NVIDIA H100 can use, with room for ≈ 254K tokens of context.

Full analysis of Qwen3-Next-80B-A3B-Thinking-GGUF Everything that runs on NVIDIA H100 Get the Q6_K file on Hugging Face
ollama run hf.co/Qwen/Qwen3-Next-80B-A3B-Thinking-GGUF:Q6_K

Files and context on NVIDIA H100

Each file of Qwen3-Next-80B-A3B-Thinking-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 H100 Context (16-bit)Context (8-bit)
Qwen3-Next-80B-A3B-Thinking159 GBDoesn't fit——
Q8_084.8 GBDoesn't fit——
Q6_K65.5 GBTight254K256K
Q5_K_M56.7 GBFits256K256K
Q5_055.0 GBFits256K256K
Q4_K_M48.4 GBFits256K256K

Qwen3-Next-80B-A3B-Thinking-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.