Stable Diffusion 3.5 Medium on NVIDIA GeForce RTX 4060

Can the NVIDIA GeForce RTX 4060 run Stable Diffusion 3.5 Medium?

Yes, it runs well (encoder in RAM)

Runs well (encoder in RAM). At FP8 it needs about 4.8 GB of 8.0 GB usable and takes about 20 s per image.

Best precision: FP8
Memory mode: Text encoder offloaded
Time per image: 20 s
Output: 1024×1024, 40 steps

Best app to run it on the NVIDIA GeForce RTX 4060

On Windows

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

On Linux

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Stable Diffusion 3.5 Medium

Quantized files · GGUF for ComfyUI

Smaller GGUF versions for ComfyUI (with the ComfyUI-GGUF node). No sign-in needed; the model’s license still applies.

huggingface.co/city96/stable-diffusion-3.5-medium-gguf (opens in a new tab)

Original weights · Hugging Face

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

huggingface.co/stabilityai/stable-diffusion-3.5-medium (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Official repo · GitHub

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

github.com/Stability-AI/sd3.5 (opens in a new tab)

git clone https://github.com/Stability-AI/sd3.5

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at FP8, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs wellencoder in RAM: How well it runs on the NVIDIA GeForce RTX 4060: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	25.6 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	20.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	10.5 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	13.8 / 15
Match score	69.9 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every precision on the NVIDIA GeForce RTX 4060

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	7.3 GB	8.0 GB	23 s	Text encoder offloaded	Runs welltight fit · encoder in RAM	58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	4.8 GB	8.0 GB	20 s	Text encoder offloaded	Runs wellencoder in RAM	56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`Q8 GGUF`	5.0 GB	8.0 GB	26 s	Text encoder offloaded	Runs wellencoder in RAM	57Good quality (B) · 57 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)

Other hardware that runs it

58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX FP16 · 6.7 s · Runs great
58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 FP16 · 6.0 s · Runs great
57Good quality (B) · 57 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8 GGUF · 9.2 s · Runs great
57Good quality (B) · 57 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q8 GGUF · 9.7 s · Runs great
57Good quality (B) · 57 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q8 GGUF · 9.2 s · Runs great
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER FP8 · 8.6 s · Runs great

Quick answers

How much memory does Stable Diffusion 3.5 Medium need on the RTX 4060 8GB?

At FP8 it needs about 4.8 GB. The RTX 4060 8GB has 8.0 GB usable.

How long does Stable Diffusion 3.5 Medium take on the RTX 4060 8GB?

About 20 s per image at FP8 and default settings, an estimate scaled from a reference timing by this hardware’s compute speed.

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.