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

Can I run Qwen3-Next-80B-A3B-Thinking on an RTX 4090?

No

Even its smallest file (4-bit (estimate), 45.7 GB) is more than an RTX 4090 can hold (21.6 GB usable): it needs 3 of them.

Full analysis of Qwen3-Next-80B-A3B-Thinking Everything that runs on RTX 4090

Files and context on RTX 4090

Each file of Qwen3-Next-80B-A3B-Thinking (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 RTX 4090 Context (16-bit)Context (8-bit)
As published163 GBDoesn't fit——
Qwen3-Next-80B-A3B-ThinkingQwen/Qwen3-Next-80B-A3B-Thinking-GGUF159 GBDoesn't fit——
Q8_0Qwen/Qwen3-Next-80B-A3B-Thinking-GGUF84.8 GBDoesn't fit——
Q6_KQwen/Qwen3-Next-80B-A3B-Thinking-GGUF65.5 GBDoesn't fit——
Q5_K_MQwen/Qwen3-Next-80B-A3B-Thinking-GGUF56.7 GBDoesn't fit——
Q5_0Qwen/Qwen3-Next-80B-A3B-Thinking-GGUF55.0 GBDoesn't fit——
Q4_K_MQwen/Qwen3-Next-80B-A3B-Thinking-GGUF48.4 GBDoesn't fit——

Qwen3-Next-80B-A3B-Thinking on other hardware

Popular models that run on RTX 4090

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.