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

RX 7900 XT 20 GB for local AI

Which image and video models run on the RX 7900 XT 20 GB, which file to download for each, and how much VRAM they need.

AMD20 GB GDDR6 · 320-bit · 800 GB/s · RDNA 3Data 2026-09-25
VRAM20 GB
MemoryGDDR6
Bus320-bit
Bandwidth800 GB/s
ArchitectureRDNA 3
Launched2022-12
Launch price$899
Runs well32 of 49

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

01What runs on it

ModelVerdictBest fileSizeNeeded
image models
FLUX.1 [dev]Runs wellQ8_012.7 GB15.0 GB
FLUX.1 [schnell]Runs wellQ8_012.7 GB15.0 GB
FLUX.1 Kontext [dev]Runs wellQ8_012.7 GB15.3 GB
FLUX.1 Krea [dev]Runs wellQ8_012.7 GB15.0 GB
FLUX.1 Fill [dev]Runs wellQ8_012.7 GB15.3 GB
FLUX.2 [dev]TightQ3_K_M16.0 GB19.3 GB
FLUX.2 [klein] 9BRuns wellQ8_010.0 GB12.3 GB
FLUX.2 [klein] 4BRuns well16-bit7.8 GB9.6 GB
Krea 2 (Turbo)Runs wellQ8_013.7 GB16.3 GB
Qwen-ImageRunsQ6_K16.8 GB19.6 GB
Qwen-Image-Edit (2511)RunsQ6_K16.9 GB19.9 GB
Qwen-Image 2.1Runs well16-bit14.2 GB16.5 GB
Z-Image TurboRuns well16-bit12.3 GB14.3 GB
Z-Image (base)Runs well16-bit12.3 GB14.3 GB
Ideogram 4RunsQ5_17.3 GB17.0 GB
Boogu-Image (Turbo)Runs wellQ8_011.6 GB14.2 GB
ERNIE-Image (Turbo)Runs well16-bit16.1 GB18.4 GB
HiDream-O1-ImageRuns well16-bit16.4 GB19.2 GB
Mage-Flow (Microsoft)Runs well16-bit8.2 GB10.0 GB
Lumina Image 2.0Runs well16-bit5.2 GB7.0 GB
HiDream-I1 (Full)Runs wellFP817.1 GB19.9 GB
HiDream-I1 (Dev)Runs wellFP817.1 GB19.9 GB
Stable Diffusion 3.5 LargeRuns well16-bit16.5 GB18.8 GB
Stable Diffusion 3.5 MediumRuns well16-bit5.1 GB6.9 GB
Chroma1-HDRuns wellQ8_09.7 GB12.0 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 2.1RunsQ6_K15.7 GB19.0 GB
video models
Wan 2.1 T2V 14BRuns wellFP814.3 GB18.6 GB
Wan 2.1 T2V 1.3BRuns well16-bit2.8 GB5.6 GB
Wan 2.1 I2V 14B 480PRunsQ6_K14.2 GB18.5 GB
Wan 2.1 I2V 14B 720PRunsQ5_K_M12.7 GB19.5 GB
Wan 2.1 VACE 14BRunsQ6_K14.5 GB19.3 GB
Wan 2.2 T2V A14BRuns wellQ8_015.4 GB19.7 GB
Wan 2.2 I2V A14BRuns wellQ8_015.4 GB19.7 GB
Wan 2.2 TI2V 5BRuns well16-bit10.0 GB13.8 GB
Wan 2.2 Animate 14BRunsQ6_K14.6 GB19.9 GB
Wan Animate 2 (14B)RunsQ6_K14.2 GB19.5 GB
Wan 2.2 S2V 14BRunsQ5_K_M15.0 GB19.8 GB
SCAIL-2 (character animation)RunsQ6_K14.2 GB19.5 GB
HunyuanVideo (13B, original)Runs wellQ8_014.0 GB18.3 GB
LTX-Video 13B (0.9.8)Runs wellQ8_014.0 GB18.3 GB
HunyuanVideo 1.5Runs wellQ8_09.0 GB13.3 GB
LTX-2 (19B)RunsQ5_K_M14.3 GB19.1 GB
LTX-2.3 (22B)RunsQ4_K_M14.3 GB19.1 GB
LTX-2.5 (22B)RunsQ4_K_M15.1 GB19.9 GB
MiniMax H3 (33B)Offload onlyQ3_K_M15.6 GB21.4 GB
MiniMax H3 PrunedRunsQ5_K_M14.1 GB19.9 GB

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

02Good to know

ComfyUI supports AMD GPUs on Windows officially since v0.7.0 (January 2026), through ROCm. Memory works the same as on NVIDIA, so the fit verdicts apply. Some custom nodes are NVIDIA-only. RDNA 3 has no FP8 compute, so FP8 files save memory but give no speed-up.

03Measured and reported results

No measured results yet. Send yours.