Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

RTX 4080 16 GB for local AI

Which image and video models run on the RTX 4080 16 GB, which file to download for each, and how much VRAM they need.

NVIDIA16 GB GDDR6X · 256-bit · 716.8 GB/s · Ada LovelaceData 2026-09-25
VRAM16 GB
MemoryGDDR6X
Bus256-bit
Bandwidth716.8 GB/s
ArchitectureAda Lovelace
Launched2022-11
Launch price$1,199
Runs well25 of 49

Specs: www.nvidia.com · launch: en.wikipedia.org

01What runs on it

ModelVerdictBest fileSizeNeeded
image models
FLUX.1 [dev]Runs wellFP811.9 GB14.2 GB
FLUX.1 [schnell]Runs wellFP811.9 GB14.2 GB
FLUX.1 Kontext [dev]Runs wellFP811.9 GB14.5 GB
FLUX.1 Krea [dev]Runs wellFP811.9 GB14.2 GB
FLUX.1 Fill [dev]Runs wellQ8_012.7 GB15.3 GB
FLUX.2 [dev]Offload onlyQ2_K12.9 GB16.2 GB
FLUX.2 [klein] 9BRuns wellFP89.4 GB11.7 GB
FLUX.2 [klein] 4BRuns well16-bit7.8 GB9.6 GB
Krea 2 (Turbo)Runs wellFP813.1 GB15.7 GB
Qwen-ImageRunsQ4_K_M13.1 GB15.9 GB
Qwen-Image-Edit (2511)TightQ3_K_M9.9 GB12.9 GB
Qwen-Image 2.1Runs wellQ8_07.6 GB9.9 GB
Z-Image TurboRuns well16-bit12.3 GB14.3 GB
Z-Image (base)Runs well16-bit12.3 GB14.3 GB
Ideogram 4RunsQ4_16.2 GB14.7 GB
Boogu-Image (Turbo)Runs wellFP810.3 GB12.9 GB
ERNIE-Image (Turbo)Runs wellQ8_08.7 GB11.0 GB
HiDream-O1-ImageRuns wellFP88.1 GB10.9 GB
Mage-Flow (Microsoft)Runs well16-bit8.2 GB10.0 GB
Lumina Image 2.0Runs well16-bit5.2 GB7.0 GB
HiDream-I1 (Full)RunsQ5_K_M13.0 GB15.8 GB
HiDream-I1 (Dev)RunsQ5_K_M13.0 GB15.8 GB
Stable Diffusion 3.5 LargeRuns wellQ8_08.8 GB11.1 GB
Stable Diffusion 3.5 MediumRuns well16-bit5.1 GB6.9 GB
Chroma1-HDRuns wellFP89.2 GB11.5 GB
SDXL 1.0Runs well16-bit6.9 GB7.1 GB
Illustrious XL / Pony (SDXL anime)Runs well16-bit6.9 GB7.1 GB
Stable Diffusion 1.5Runs well16-bit2.1 GB3.3 GB
HunyuanImage 2.1RunsQ4_K_M11.3 GB14.6 GB
video models
Wan 2.1 T2V 14BRunsQ5_K_M11.3 GB15.6 GB
Wan 2.1 T2V 1.3BRuns well16-bit2.8 GB5.6 GB
Wan 2.1 I2V 14B 480PRunsQ4_K_M11.3 GB15.6 GB
Wan 2.1 I2V 14B 720PTightQ3_K_M8.6 GB15.4 GB
Wan 2.1 VACE 14BTightQ3_K_S7.8 GB12.6 GB
Wan 2.2 T2V A14BRunsQ5_K_M10.8 GB15.1 GB
Wan 2.2 I2V A14BRunsQ5_K_M10.8 GB15.1 GB
Wan 2.2 TI2V 5BRuns well16-bit10.0 GB13.8 GB
Wan 2.2 Animate 14BTightQ3_K_M8.6 GB13.9 GB
Wan Animate 2 (14B)TightQ3_K_M8.6 GB13.9 GB
Wan 2.2 S2V 14BTightQ2_K9.5 GB14.3 GB
SCAIL-2 (character animation)TightQ3_K_M9.1 GB14.4 GB
HunyuanVideo (13B, original)RunsQ6_K11.0 GB15.3 GB
LTX-Video 13B (0.9.8)RunsQ6_K10.9 GB15.2 GB
HunyuanVideo 1.5Runs wellFP88.3 GB12.6 GB
LTX-2 (19B)TightQ3_K_M10.1 GB14.9 GB
LTX-2.3 (22B)TightQ3_K_M10.8 GB15.6 GB
LTX-2.5 (22B)TightQ2_K8.8 GB13.6 GB
MiniMax H3 (33B)Offload onlyQ4_K_M19.9 GB25.7 GB
MiniMax H3 PrunedTightQ3_K_M8.9 GB14.7 GB

Calculated from real file sizes plus working memory. How the numbers work.

02Good to know

The RTX 4080 16 GB is an Ada Lovelace GPU with hardware FP8, so ComfyUI can compute Comfy-Org's FP8 files natively: small and fast. (Plain FP8 files use FP8 maths with the --fast fp8_matrix_mult option.)

03Measured and reported results

LabelModelSetupResultPeak VRAMDateSource
reportedFLUX.1 devfp8_e4m3fn weight_dtype · 1024x1024 · 20 steps
“weight_dtype (fp8_e4m3fn) with --fast (13sec)”
ComfyUI 'RTX 4090 benchmarks - FLUX model' thread; OP settings 1024x1024, 20 steps; Aug 2024 ComfyUI/PyTorch 2.5 dev; with --fast flag (same poster: 19sec without --fast, 28sec def
13 s / image—2024-08-23github.com →

Reported results are other people's numbers, copied as published, with a link. Settings, drivers and ComfyUI versions differ, so compare them with care. Send yours.