Support Matrix#
Models#
Model Name |
Model ID |
Publisher |
|
|---|---|---|---|
FLUX.1-dev |
black-forest-labs/flux.1-dev |
Black Forest Labs |
base, canny, depth |
FLUX.1-Kontext-dev |
black-forest-labs/flux.1-kontext-dev |
Black Forest Labs |
base |
FLUX.1-schnell |
black-forest-labs/flux.1-schnell |
Black Forest Labs |
base |
Stable Diffusion 3.5 Large |
stabilityai/stable-diffusion-3.5-large |
Stability AI |
base, canny, depth |
Supported Hardware#
Black Forest Labs / FLUX.1-dev#
System Requirements |
GPU Memory |
RAM |
OS |
CPU |
|---|---|---|---|---|
Minimal |
16GB |
40GB |
Linux/WSL2 |
x86_64 |
Recommended |
32GB |
64GB |
Linux/WSL2 |
x86_64 |
NVIDIA supports the FLUX.1-dev model on the following GPU models, using the optimized TensorRT engine.
GPU |
GPU Memory (GB) |
Precision |
|---|---|---|
GeForce RTX 5090 |
32 |
FP4, FP8 |
GeForce RTX 5090 Laptop |
24 |
FP4, FP8 |
GeForce RTX 5080 |
16 |
FP4, FP8 |
GeForce RTX 5080 Laptop |
24 |
FP4, FP8 |
GeForce RTX 5070 TI |
16 |
FP4, FP8 |
GeForce RTX 4090 |
24 |
FP8 |
GeForce RTX 4090 Laptop |
16 |
FP8 |
GeForce RTX 4080 Super |
16 |
FP8 |
GeForce RTX 4080 |
16 |
FP8 |
NVIDIA RTX 6000 Ada Generation |
48 |
FP8 |
GeForce RTX 5090D |
32 |
FP4, FP8 |
GeForce RTX 4090D |
24 |
FP8 |
H100 SXM |
80 |
FP8 |
L40S |
48 |
FP8 |
L40 |
48 |
FP8 |
Black Forest Labs / FLUX.1-schnell#
System Requirements |
GPU Memory |
RAM |
OS |
CPU |
|---|---|---|---|---|
Minimal |
16GB |
40GB |
Linux/WSL2 |
x86_64 |
Recommended |
32GB |
40GB |
Linux/WSL2 |
x86_64 |
NVIDIA supports the FLUX.1-schnell model on the following GPU models, using the optimized TensorRT engine.
GPU |
GPU Memory (GB) |
Precision |
|---|---|---|
GeForce RTX 5090 |
32 |
FP4, FP8 |
GeForce RTX 5090 Laptop |
24 |
FP4, FP8 |
GeForce RTX 5080 |
16 |
FP4, FP8 |
GeForce RTX 5080 Laptop |
24 |
FP4, FP8 |
GeForce RTX 5070 TI |
16 |
FP4, FP8 |
GeForce RTX 4090 |
24 |
FP8 |
GeForce RTX 4090 Laptop |
16 |
FP8 |
GeForce RTX 4080 Super |
16 |
FP8 |
GeForce RTX 4080 |
16 |
FP8 |
NVIDIA RTX 6000 Ada Generation |
48 |
FP8 |
GeForce RTX 5090D |
32 |
FP4, FP8 |
GeForce RTX 4090D |
24 |
FP8 |
H100 SXM |
80 |
FP8 |
L40S |
48 |
FP8 |
L40 |
48 |
FP8 |
Black Forest Labs / FLUX.1-Kontext-dev#
System Requirements |
GPU Memory |
RAM |
OS |
CPU |
|---|---|---|---|---|
Minimal |
16GB |
40GB |
Linux/WSL2 |
x86_64 |
Recommended |
32GB |
64GB |
Linux/WSL2 |
x86_64 |
NVIDIA supports the FLUX.1-Kontext-dev model on the following GPU models, using the optimized TensorRT engine.
GPU |
GPU Memory (GB) |
Precision |
|---|---|---|
GeForce RTX 5090 |
32 |
FP4, FP8 |
GeForce RTX 5090 Laptop |
24 |
FP4, FP8 |
GeForce RTX 5080 |
16 |
FP4, FP8 |
GeForce RTX 5080 Laptop |
24 |
FP4, FP8 |
GeForce RTX 5070 TI |
16 |
FP4, FP8 |
GeForce RTX 4090 |
24 |
FP8 |
GeForce RTX 4090 Laptop |
16 |
FP8 |
GeForce RTX 4080 Super |
16 |
FP8 |
GeForce RTX 4080 |
16 |
FP8 |
NVIDIA RTX PRO 6000 Blackwell Workstation Edition |
96 |
FP4, FP8 |
NVIDIA RTX PRO 6000 Blackwell Server Edition |
96 |
FP4, FP8 |
NVIDIA RTX 6000 Ada Generation |
48 |
FP8 |
H100 SXM |
80 |
FP8 |
L40S |
48 |
FP8 |
Stability AI / Stable Diffusion 3.5 Large#
System Requirements |
GPU Memory |
RAM |
OS |
CPU |
|---|---|---|---|---|
Minimal |
24GB |
48GB |
Linux/WSL2 |
x86_64 |
Recommended |
32GB |
64GB |
Linux/WSL2 |
x86_64 |
NVIDIA supports the Stable Diffusion 3.5 Large model on the following GPU models, using the optimized TensorRT engine.
GPU |
GPU Memory (GB) |
Precision |
|---|---|---|
A100 SXM |
80 |
BF16 |
H100 SXM |
80 |
BF16 |
L40S |
48 |
BF16 |
Software#
NVIDIA Driver#
NVIDIA NIM for Visual Generative AI is built on top of Triton Inference Server (25.01) which requires NVIDIA Driver release 560 or later.
Refer to the Release Notes for the detailed list of supported drivers.
NVIDIA Container Toolkit#
Your Docker environment must support NVIDIA GPUs. Refer to Installing the NVIDIA Container Toolkit for more information.