Qwen3 30B-A3B Instruct 2507 on NVIDIA GeForce RTX 5090

Can the NVIDIA GeForce RTX 5090 run Qwen3 30B-A3B Instruct 2507?

88 pts

Yes, it runs well

Runs well. At Q5_K_M it needs about 24.7 GB of 32.0 GB usable, with an estimated speed of 275 tok/s.

Best quant: Q5_K_M
Generation speed: 275 tok/s
Prompt processing: 22,865 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 80K

Download Qwen3 30B-A3B Instruct 2507

Recommended for the NVIDIA GeForce RTX 5090: Q5_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run qwen3:30b-instruct

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q5_K_M file (opens in a new tab)

huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF:Q5_K_M

Original weights · Hugging Face

Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers.

huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Alibaba. The weights themselves download from Hugging Face.

github.com/QwenLM/Qwen3 (opens in a new tab)

git clone https://github.com/QwenLM/Qwen3

Qwen’s main repo, renamed from Qwen2.5 to Qwen3; it still documents Qwen2.5.

Links checked 1 week ago against Hugging Face, Ollama and GitHub.

How the S grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	33.6 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Total	88.6 / 100	88 ptsExcellent (S) · 88 of 100 points: Model quality 33.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA GeForce RTX 5090

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	15.2 GB	32.0 GB	547 tok/s	Runs well	75 ptsGreat (A) · 75 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15	GGUF (opens in a new tab)
`Q3_K_M`	18.0 GB	32.0 GB	431 tok/s	Runs well	82 ptsGreat (A) · 82 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.0/15	GGUF (opens in a new tab)
`Q4_K_M`	21.6 GB	32.0 GB	333 tok/s	Runs well	87 ptsExcellent (S) · 87 of 100 points: Model quality 32.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q5_K_M`	24.7 GB	32.0 GB	275 tok/s	Runs well	88 ptsExcellent (S) · 88 of 100 points: Model quality 33.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q6_K`	28.0 GB	32.0 GB	231 tok/s	Tight fit	88 ptsExcellent (S) · 88 of 100 points: Model quality 34.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q8_0`	35.4 GB	32.0 GB	45.9 tok/s	Runs with offload	74 ptsGreat (A) · 74 of 100 points: Model quality 34.7/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF (opens in a new tab)
`F16`	64.1 GB	32.0 GB	—	Won't run	10 ptsWon't run (F) · 10 of 100 points: Model quality 10.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

89 ptsExcellent (S) · 89 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Apple M4 Max (64 GB) Q8_0 · 44.5 tok/s
89 ptsExcellent (S) · 89 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA RTX PRO 6000 Blackwell F16 · 78.2 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.6/15 Apple M1 Max (64 GB) Q6_K · 44.4 tok/s
87 ptsExcellent (S) · 87 of 100 points: Model quality 32.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.7/15 Apple M4 Pro (48 GB) Q4_K_M · 43.7 tok/s
86 ptsExcellent (S) · 86 of 100 points: Model quality 32.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q4_K_M · 154 tok/s

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.