Datasheet for local AI50 models99 GPUsData read 2026-10-01
No adsNo tracking
Check my GPU →

Radeon 8065S (Gorgon Halo) 160 GB for local AI

Which image and video models run on the Radeon 8065S (Gorgon Halo) 160 GB, which file to download for each, and how much VRAM they need.

AMD160 GB LPDDR5X-8533 (shared system memory, up to 192 GB total) · 256-bit · 273 GB/s · RDNA 3.5Data 2026-10-01
VRAM160 GB
MemoryLPDDR5X-8533 (shared system memory, up to 192 GB total)
Bus256-bit
Bandwidth273 GB/s
ArchitectureRDNA 3.5
Launched2026-09
Power—
Runs well50 of 50

Specs: www.amd.com · launch: www.techspot.com

01What runs on it

ModelVerdictBest fileSizeNeeded
image models
FLUX.1 [dev]Runs well16-bit23.8 GB26.1 GB
FLUX.1 [schnell]Runs well16-bit23.8 GB26.1 GB
FLUX.1 Kontext [dev]Runs well16-bit23.8 GB26.4 GB
FLUX.1 Krea [dev]Runs well16-bit23.8 GB26.1 GB
FLUX.1 Fill [dev]Runs well16-bit23.8 GB26.4 GB
FLUX.2 [dev]Runs well16-bit64.4 GB67.7 GB
FLUX.2 [klein] 9BRuns well16-bit18.2 GB20.5 GB
FLUX.2 [klein] 4BRuns well16-bit7.8 GB9.6 GB
Krea 2 (Turbo)Runs well16-bit26.3 GB28.9 GB
Qwen-ImageRuns well16-bit40.9 GB43.7 GB
Qwen-Image-Edit (2511)Runs well16-bit40.9 GB43.9 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 4Runs wellQ8_010.1 GB22.6 GB
Boogu-Image (Turbo)Runs well16-bit20.6 GB23.2 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
Ming-Image 0.1 DesignRuns well16-bit12.3 GB14.6 GB
Lumina Image 2.0Runs well16-bit5.2 GB7.0 GB
HiDream-I1 (Full)Runs well16-bit34.2 GB37.0 GB
HiDream-I1 (Dev)Runs well16-bit34.2 GB37.0 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 well16-bit17.8 GB20.1 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 2.1Runs well16-bit34.9 GB38.2 GB
video models
Wan 2.1 T2V 14BRuns well16-bit28.6 GB32.9 GB
Wan 2.1 T2V 1.3BRuns well16-bit2.8 GB5.6 GB
Wan 2.1 I2V 14B 480PRuns well16-bit32.8 GB37.1 GB
Wan 2.1 I2V 14B 720PRuns well16-bit32.8 GB39.6 GB
Wan 2.1 VACE 14BRuns well16-bit34.7 GB39.5 GB
Wan 2.2 T2V A14BRuns well16-bit28.6 GB32.9 GB
Wan 2.2 I2V A14BRuns well16-bit28.6 GB32.9 GB
Wan 2.2 TI2V 5BRuns well16-bit10.0 GB13.8 GB
Wan 2.2 Animate 14BRuns well16-bit34.5 GB39.8 GB
Wan Animate 2 (14B)Runs well16-bit32.8 GB38.1 GB
Wan 2.2 S2V 14BRuns well16-bit32.6 GB37.4 GB
SCAIL-2 (character animation)Runs well16-bit32.8 GB38.1 GB
HunyuanVideo (13B, original)Runs well16-bit25.6 GB29.9 GB
LTX-Video 13B (0.9.8)Runs well16-bit28.6 GB32.9 GB
HunyuanVideo 1.5Runs well16-bit16.7 GB21.0 GB
LTX-2 (19B)Runs well16-bit37.8 GB42.6 GB
LTX-2.3 (22B)Runs well16-bit42.0 GB46.8 GB
LTX-2.5 (22B)Runs well16-bit42.0 GB46.8 GB
MiniMax H3 (33B)Runs well16-bit66.3 GB72.1 GB
MiniMax H3 PrunedRuns well16-bit40.2 GB46.0 GB

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

02Good to know

This is the integrated GPU of the Ryzen AI Max+ PRO 495 (Gorgon Halo, September 2026), a refresh of Strix Halo. It uses system memory: on a 192 GB machine up to 160 GB can go to the GPU, so it holds models no graphics card can. The GPU itself is the same 40-compute-unit RDNA 3.5 design as Strix Halo with slightly faster memory (about 273 GB/s), and it has no FP8 hardware. Treat the verdicts here as 'it fits', not 'it is fast'. What unified memory means for local AI →

03Measured and reported results

No measured results yet. Send yours.