Qwen-Image on NVIDIA GeForce RTX 4070 SUPER

Can the NVIDIA GeForce RTX 4070 SUPER run Qwen-Image?

11 pts

No, it doesn’t fit

No. Qwen-Image needs about 13.3 GB even at FP8; the NVIDIA GeForce RTX 4070 SUPER has 12.0 GB usable.

Download Qwen-Image

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen-Image (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/Qwen-Image (opens in a new tab)

git clone https://github.com/QwenLM/Qwen-Image

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How the F 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.	11.6 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	0.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	0.0 / 15
Total	11.6 / 100	11 ptsWon't run (F) · 11 of 100 points: Model quality 11.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

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

Every precision on the NVIDIA GeForce RTX 4070 SUPER

Precision	Memory needed	Available	Time per output	Memory mode	Fit	Grade · points	Download
`FP16`	20.4 GB	12.0 GB	—	—	Won't run	11 ptsWon't run (F) · 11 of 100 points: Model quality 11.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Original weights (opens in a new tab)
`FP8`	13.3 GB	12.0 GB	—	—	Won't run	11 ptsWon't run (F) · 11 of 100 points: Model quality 11.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Original weights (opens in a new tab)

Hardware that can run it

85 ptsExcellent (S) · 85 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 5.8/15, Memory use 15.0/15 NVIDIA RTX PRO 6000 Blackwell FP16 · 66 s
83 ptsGreat (A) · 83 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 3.6/15, Memory use 15.0/15 AMD Ryzen AI Max+ 395 (128 GB) FP16 · 2.9 min
81 ptsGreat (A) · 81 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 2.1/15, Memory use 15.0/15 Apple M4 Max (128 GB) FP16 · 8.8 min
80 ptsGreat (A) · 80 of 100 points: Model quality 38.8/45, Memory fit 25.0/25, Speed 2.2/15, Memory use 15.0/15 Apple M4 Max (64 GB) FP8 · 7.9 min
80 ptsGreat (A) · 80 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 3.5/15, Memory use 12.8/15 NVIDIA GB10 (128 GB) FP16 · 3.1 min
80 ptsGreat (A) · 80 of 100 points: Model quality 38.8/45, Memory fit 25.0/25, Speed 1.8/15, Memory use 15.0/15 Apple M1 Max (64 GB) FP8 · 12.1 min

Models that do run on the NVIDIA GeForce RTX 4070 SUPER

90 ptsExcellent (S) · 90 of 100 points: Model quality 35.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Z-Image Turbo Q4 GGUF · 5.7 s
89 ptsExcellent (S) · 89 of 100 points: Model quality 34.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 FLUX.2 [klein] 4B FP8 · 1.7 s
85 ptsExcellent (S) · 85 of 100 points: Model quality 35.2/45, Memory fit 20.0/25, Speed 15.0/15, Memory use 15.0/15 FLUX.2 [klein] 9B Q4 GGUF · 4.3 s
82 ptsGreat (A) · 82 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Juggernaut XL v9 FP16 · 8.5 s
82 ptsGreat (A) · 82 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 RealVisXL V5.0 FP16 · 8.5 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.