Radeon 8060S (Strix Halo) 96 GB for local AI
Which image and video models run on the Radeon 8060S (Strix Halo) 96 GB, which file to download for each, and how much VRAM they need.
VRAM96 GB
MemoryLPDDR5X (shared system memory)
Bus256-bit
Bandwidth256 GB/s
ArchitectureRDNA 3.5
Launched2025-01
Power—
Runs well49 of 49
Specs: www.amd.com · launch: newsroom.amd.com
01What runs on it
| Model | Verdict | Best file | Size | Needed |
|---|---|---|---|---|
| image models | ||||
| FLUX.1 [dev] | Runs well | 16-bit | 23.8 GB | 26.1 GB |
| FLUX.1 [schnell] | Runs well | 16-bit | 23.8 GB | 26.1 GB |
| FLUX.1 Kontext [dev] | Runs well | 16-bit | 23.8 GB | 26.4 GB |
| FLUX.1 Krea [dev] | Runs well | 16-bit | 23.8 GB | 26.1 GB |
| FLUX.1 Fill [dev] | Runs well | 16-bit | 23.8 GB | 26.4 GB |
| FLUX.2 [dev] | Runs well | 16-bit | 64.4 GB | 67.7 GB |
| FLUX.2 [klein] 9B | Runs well | 16-bit | 18.2 GB | 20.5 GB |
| FLUX.2 [klein] 4B | Runs well | 16-bit | 7.8 GB | 9.6 GB |
| Krea 2 (Turbo) | Runs well | 16-bit | 26.3 GB | 28.9 GB |
| Qwen-Image | Runs well | 16-bit | 40.9 GB | 43.7 GB |
| Qwen-Image-Edit (2511) | Runs well | 16-bit | 40.9 GB | 43.9 GB |
| Qwen-Image 2.1 | Runs well | 16-bit | 14.2 GB | 16.5 GB |
| Z-Image Turbo | Runs well | 16-bit | 12.3 GB | 14.3 GB |
| Z-Image (base) | Runs well | 16-bit | 12.3 GB | 14.3 GB |
| Ideogram 4 | Runs well | Q8_0 | 10.1 GB | 22.6 GB |
| Boogu-Image (Turbo) | Runs well | 16-bit | 20.6 GB | 23.2 GB |
| ERNIE-Image (Turbo) | Runs well | 16-bit | 16.1 GB | 18.4 GB |
| HiDream-O1-Image | Runs well | 16-bit | 16.4 GB | 19.2 GB |
| Mage-Flow (Microsoft) | Runs well | 16-bit | 8.2 GB | 10.0 GB |
| Lumina Image 2.0 | Runs well | 16-bit | 5.2 GB | 7.0 GB |
| HiDream-I1 (Full) | Runs well | 16-bit | 34.2 GB | 37.0 GB |
| HiDream-I1 (Dev) | Runs well | 16-bit | 34.2 GB | 37.0 GB |
| Stable Diffusion 3.5 Large | Runs well | 16-bit | 16.5 GB | 18.8 GB |
| Stable Diffusion 3.5 Medium | Runs well | 16-bit | 5.1 GB | 6.9 GB |
| Chroma1-HD | Runs well | 16-bit | 17.8 GB | 20.1 GB |
| SDXL 1.0 | Runs well | 16-bit | 6.9 GB | 7.1 GB |
| Illustrious XL / Pony (SDXL anime) | Runs well | 16-bit | 6.9 GB | 7.1 GB |
| Stable Diffusion 1.5 | Runs well | 16-bit | 2.1 GB | 3.3 GB |
| HunyuanImage 2.1 | Runs well | 16-bit | 34.9 GB | 38.2 GB |
| video models | ||||
| Wan 2.1 T2V 14B | Runs well | 16-bit | 28.6 GB | 32.9 GB |
| Wan 2.1 T2V 1.3B | Runs well | 16-bit | 2.8 GB | 5.6 GB |
| Wan 2.1 I2V 14B 480P | Runs well | 16-bit | 32.8 GB | 37.1 GB |
| Wan 2.1 I2V 14B 720P | Runs well | 16-bit | 32.8 GB | 39.6 GB |
| Wan 2.1 VACE 14B | Runs well | 16-bit | 34.7 GB | 39.5 GB |
| Wan 2.2 T2V A14B | Runs well | 16-bit | 28.6 GB | 32.9 GB |
| Wan 2.2 I2V A14B | Runs well | 16-bit | 28.6 GB | 32.9 GB |
| Wan 2.2 TI2V 5B | Runs well | 16-bit | 10.0 GB | 13.8 GB |
| Wan 2.2 Animate 14B | Runs well | 16-bit | 34.5 GB | 39.8 GB |
| Wan Animate 2 (14B) | Runs well | 16-bit | 32.8 GB | 38.1 GB |
| Wan 2.2 S2V 14B | Runs well | 16-bit | 32.6 GB | 37.4 GB |
| SCAIL-2 (character animation) | Runs well | 16-bit | 32.8 GB | 38.1 GB |
| HunyuanVideo (13B, original) | Runs well | 16-bit | 25.6 GB | 29.9 GB |
| LTX-Video 13B (0.9.8) | Runs well | 16-bit | 28.6 GB | 32.9 GB |
| HunyuanVideo 1.5 | Runs well | 16-bit | 16.7 GB | 21.0 GB |
| LTX-2 (19B) | Runs well | 16-bit | 37.8 GB | 42.6 GB |
| LTX-2.3 (22B) | Runs well | 16-bit | 42.0 GB | 46.8 GB |
| LTX-2.5 (22B) | Runs well | 16-bit | 42.0 GB | 46.8 GB |
| MiniMax H3 (33B) | Runs well | 16-bit | 66.3 GB | 72.1 GB |
| MiniMax H3 Pruned | Runs well | 16-bit | 40.2 GB | 46.0 GB |
Calculated from real file sizes plus working memory. How the numbers work.
02Good to know
This is an integrated GPU that uses system memory. AMD states that up to 96 GB of the 128 GB can be set aside as graphics memory on Windows, which is why it can hold models no consumer graphics card can. The catch is speed: the GPU itself (40 compute units) is far smaller than a big desktop card, and its memory bandwidth is a fraction of one, so each step takes much longer. Treat the verdicts here as 'it fits', not 'it is fast'.
03Measured and reported results
| Label | Model | Setup | Result | Peak VRAM | Date | Source |
|---|---|---|---|---|---|---|
| reported | FLUX.1 dev | flux1-dev full precision (23.8 GB) + t5xxl_fp16 · 1024x1024 · 20 steps “Steady state | 3.64 s/it | 77.56 s” AMD ROCm blog, Ryzen AI Max+ 395 / Radeon 8060S, 128 GB unified, Windows ComfyUI; first run 103.89 s; vendor-published measurement | 77.56 s / image · 3.64 s/it | — | 2026-07-14 | rocm.blogs.amd.com → |
| reported | LTX-2 | LTX-2 BF16 (T2V) · 1280x720 “"workflow": "LTX2-T2V-BF16.json", ... "duration_seconds": 615.0017409324646” kyuz0 Strix Halo toolbox benchmark; cold run incl. model load; resolution/frames from benchmark page; I2V = 616.16 s; steps not stated | 615 s / clip (121 frames) | — | 2026-02-13 | raw.githubusercontent.com → |
| reported | Qwen-Image | Qwen-Image-2512 BF16 + 4-step Lightning LoRA · 1328x1328 · 4 steps “"workflow": "Qwen-Image-2512-BF16-4-Step-LoRA.json", ... "duration_seconds": 75.37661480903625” kyuz0 Strix Halo ComfyUI toolbox benchmark (Ryzen AI Max, ROCm); cold run incl. model load, flags --disable-mmap --gpu-only --disable-smart-memory --cache-none; resolution from ben | 75.38 s / image | — | 2026-02-13 | raw.githubusercontent.com → |
| reported | Qwen-Image-Edit | Qwen-Image-Edit-2511 BF16 + 4-step LoRA · ~1.6MP (dynamic) · 4 steps “"workflow": "Qwen-Image-Edit-2511-BF16-4-Step-LoRA.json", ... "duration_seconds": 112.70737218856812” kyuz0 Strix Halo toolbox benchmark; cold run incl. model load; 20-step run = 667.24 s; date from run timestamp | 112.71 s / image | — | 2026-02-13 | raw.githubusercontent.com → |
| reported | Wan 2.2 T2V | Wan 2.2 T2V A14B (high+low noise experts) · 640x640 · 4 steps “Steady state | 197 s/it | 186 s/it | 26 min 51 s” AMD ROCm blog, Ryzen AI Max+ 395; s/it for high-noise / low-noise expert; 26 min 51 s = 1611 s; first run 36 min 14 s; vendor-published | 1611 s / clip (81 frames) | — | 2026-07-14 | rocm.blogs.amd.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.