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

Can the Radeon 8060S (Strix Halo) 96 GB run Boogu-Image (Turbo)?

Image model · 10.29B96 GB LPDDR5X (shared system memory) · 256-bit · 256 GB/s · RDNA 3.5Data 2026-09-25
Runs well
Yes — and comfortably.

Download 16-bit (20.6 GB). With the model's working memory it needs about 23.2 GB, leaving 72.8 GB spare on 96 GB. Quality: the original weights.

Best file16-bit
File size20.6 GB
GPU memory needed~23.2 GB
Shared memory37 / 128 GB
Memory map · Radeon 8060S (Strix Halo) 96 GB23.2 GB / 96 GB
048 GB96 GB
Weights 16-bit · 20.6 GBWorking memory · 1.8 GBReserve · 0.8 GBFree · 72.8 GB
calculated from real file sizes plus working memory. Not yet measured on this setup. How this works.

01What to download

PartFileFolderSize
Modelboogu_image_turbo_bf16.safetensors
16-bit · Comfy-Org/Boogu-Image
models/diffusion_models20.6 GBDownload →
Text encoderqwen3vl_8b_fp8_scaled.safetensors
Qwen3-VL 8B FP8 · Comfy-Org/Boogu-Image
models/text_encoders10.6 GBDownload →
VAEflux1_vae_bf16.safetensors
FLUX.1 VAE BF16 · Comfy-Org/Boogu-Image
models/vae0.2 GBDownload →
Total download · keep about the same free on disk31.3 GB

Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.

Shared memory: about 37.3 GB of your 128 GB. On this machine the model, the text encoder, the VAE and the operating system all use the same memory. That leaves room, so nothing has to be swapped to disk. calculated

02Every Boogu-Image file on 96 GB

FileSizeNeededOn this cardQualityDownload
16-bit ←
SAFETENSORS · Comfy-Org
20.6 GB23.2 GBfits · 72.8 GB sparethe original weightsHugging Face →
Q8_0
GGUF · realrebelai
11.6 GB14.2 GBfits · 81.8 GB sparepractically identical to the originalHugging Face →
FP8
SAFETENSORS · Comfy-Org
10.3 GB12.9 GBfits · 83.1 GB sparepractically identical to the originalHugging Face →
INT8
SAFETENSORS · Comfy-Org
11.4 GB14.0 GBfits · 82.0 GB sparepractically identical to the originalHugging Face →
Q5_1
GGUF · realrebelai
8.6 GB11.2 GBfits · 84.8 GB spareclose; small differences in fine detailHugging Face →
Q4_1
GGUF · realrebelai
7.4 GB10.0 GBfits · 86.0 GB sparegood; some loss in fine detail and textHugging Face →

Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 1.8 GB working memory for this model + 0.8 GB kept free for the system.

03The text encoder

Qwen3-VL 8B: 10.6 GB as FP8, 6.3 GB as NVFP4. ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 96 GB the FP8 encoder fits on its own, so prompt encoding stays fast.

04About this GPU

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'.

Radeon 8060S (Strix Halo) 96 GB: 96 GB LPDDR5X (shared system memory) · 256-bit · 256 GB/s · RDNA 3.5. Everything that runs on the Radeon 8060S (Strix Halo) 96 GB →

05What more VRAM would change

Nothing to gain for this model: the Radeon 8060S (Strix Halo) 96 GB already runs a top-quality file entirely in VRAM. More memory would only help with bigger images, longer clips or several models at once.

06Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run Boogu-Image on a Radeon 8060S (Strix Halo) 96 GB, send your time per image and peak VRAM and it will appear here, credited.

07Questions

How much VRAM does Boogu-Image need?

Around 10.0 GB with the smallest file (Q4_1) and 12.9 GB with an 8-bit file (FP8), counting working memory and a small system reserve. The full 16-bit file needs about 23.2 GB.

Which Boogu-Image file should I download for the Radeon 8060S (Strix Halo) 96 GB?

16-bit (20.6 GB) from Comfy-Org/Boogu-Image.

Is FP8 faster than GGUF on the Radeon 8060S (Strix Halo) 96 GB?

No. This GPU has no FP8 compute, so ComfyUI converts FP8 weights back before the maths. FP8 only saves memory here; Q8_0 GGUF is the closer-to-original 8-bit pick.

How much do I need to download for Boogu-Image on the Radeon 8060S (Strix Halo) 96 GB?

About 31.3 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 96 GB card, 48 GB of system RAM or more is recommended.