Can I run Qwen3.8-27B-MLX-5bit on an RTX 4090?

Yes, just

Its published weights (19.4 GB) fit in the 21.6 GB an RTX 4090 can use, with room for ≈ 30K tokens of context.

Full analysis of Qwen3.8-27B-MLX-5bit Everything that runs on RTX 4090 Get the weights on Hugging Face

hf download lmstudio-community/Qwen3.8-27B-MLX-5bit

Files and context on RTX 4090

Each file of Qwen3.8-27B-MLX-5bit (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	19.4 GB	Tight	30K	61K
4-bit (estimate)	15.4 GB	Fits	90K	181K

Qwen3.8-27B-MLX-5bit on other hardware

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