Can I run Xing4.0-29B-A4B on an RTX 4090?

Yes, with a GGUF version

The published weights are too big, but the IQ4_NL file from XingChen-AGI/Xing4.0-29B-A4B-GGUF (20.1 GB) fits, with room for ≈ 32K tokens of context.

Full analysis of Xing4.0-29B-A4B Everything that runs on RTX 4090 Get the IQ4_NL file on Hugging Face

ollama run hf.co/XingChen-AGI/Xing4.0-29B-A4B-GGUF:IQ4_NL

Files and context on RTX 4090

Each file of Xing4.0-29B-A4B (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 RTX 4090	Context (16-bit)	Context (8-bit)
As published	62.4 GB	Doesn't fit	—	—
IQ4_NLXingChen-AGI/Xing4.0-29B-A4B-GGUF	20.1 GB	Tight	32K	63K

Xing4.0-29B-A4B on other hardware

NVIDIA H100Yes, just
RTX 5090Yes, with a GGUF version
RTX 4090Yes, with a GGUF version
RTX 3090Yes, with a GGUF version
RTX 5060 Ti 16 GBNo
RTX 3060 12 GBNo
RTX 4060No
Mac with 32 GBYes, with a GGUF version
Mac with 64 GBYes, with a GGUF version
Mac with 128 GBYes

Popular models that run on RTX 4090

Qwen3-0.6BQwen · 752M
Qwen3-VL-8B-InstructQwen · 8.77B
gpt2openai-community · 137M
tiny-Qwen2ForCausalLM-2.5trl-internal-testing · 2.44M
Qwen3-8BQwen · 8.19B
Qwen3-Coder-30B-A3B-Instruct-GGUFunsloth · 30.5B
Qwen2.5-7B-InstructQwen · 7.62B
Qwen3.5-9BQwen · 9.65B

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.