FLUX.2 [klein] 4B on NVIDIA GeForce RTX 3060 Ti

Can the NVIDIA GeForce RTX 3060 Ti run FLUX.2 [klein] 4B?

84 pts

Yes, it runs well

Runs well. At Q8 GGUF it needs about 6.4 GB of 8.0 GB usable, with an estimated speed of 4.1 s.

Best precision: Q8 GGUF
Memory mode: Text encoder offloaded
Time per image: 4.1 s
Output: 1024×1024, 4 steps

Download FLUX.2 [klein] 4B

Recommended for the NVIDIA GeForce RTX 3060 Ti: q8_gguf. Every other precision has its own download link in the table below.

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.

Download the q8_gguf (Q8_0) file (opens in a new tab)

huggingface.co/unsloth/FLUX.2-klein-4B-GGUF (opens in a new tab)

Original weights · Hugging Face

Full-precision files from Black Forest Labs, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/black-forest-labs/FLUX.2-klein-4B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Black Forest Labs. The weights themselves download from Hugging Face.

github.com/black-forest-labs/flux2 (opens in a new tab)

git clone https://github.com/black-forest-labs/flux2

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

How the A 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.	34.7 / 45
Memory fitFull marks when everything sits in GPU or unified 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.	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	84.7 / 100	84 ptsGreat (A) · 84 of 100 points: Model quality 34.7/45, Memory fit 20.0/25, 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 precision on the NVIDIA GeForce RTX 3060 Ti

Precision	Memory needed	Available	Time per output	Memory mode	Fit	Grade · points	Download
`FP16`	4.8 GB	8.0 GB	4.4 s	Sequential CPU offload	Runs well	76 ptsGreat (A) · 76 of 100 points: Model quality 35.1/45, Memory fit 12.0/25, Speed 15.0/15, Memory use 13.9/15	Original weights (opens in a new tab)
`FP8`	6.2 GB	8.0 GB	3.2 s	Text encoder offloaded	Runs well	84 ptsGreat (A) · 84 of 100 points: Model quality 34.4/45, Memory fit 20.0/25, Speed 15.0/15, Memory use 15.0/15	Original weights (opens in a new tab)
`Q8 GGUF`	6.4 GB	8.0 GB	4.1 s	Text encoder offloaded	Runs well	84 ptsGreat (A) · 84 of 100 points: Model quality 34.7/45, Memory fit 20.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q4 GGUF`	4.6 GB	8.0 GB	4.3 s	Text encoder offloaded	Runs well	80 ptsGreat (A) · 80 of 100 points: Model quality 32.6/45, Memory fit 20.0/25, Speed 15.0/15, Memory use 13.3/15	GGUF (opens in a new tab)

Other hardware that runs it

90 ptsExcellent (S) · 90 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX FP16 · 1.1 s
90 ptsExcellent (S) · 90 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 FP16 · 1.9 s
90 ptsExcellent (S) · 90 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 FP16 · 1.0 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 AMD Radeon RX 9070 XT Q8 GGUF · 1.5 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 GeForce RTX 4060 Ti 16GB Q8 GGUF · 3.1 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 GeForce RTX 4070 Ti SUPER Q8 GGUF · 1.8 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.