Can the Radeon 8060S (Strix Halo) 96 GB run FLUX.2 [klein] 4B?
Yes. 16-bit fits on the Radeon 8060S (Strix Halo) 96 GB with 86.4 GB to spare.
16-bit (7.8 GB) needs about 9.6 GB in use, so 86.4 GB of the 96 GB stays free: room for a larger image, a LoRA or a ControlNet.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux-2-klein-4b.safetensors 16-bit · black-forest-labs/FLUX.2-klein-4B | models/diffusion_models | 7.8 GB | Download → |
| Text encoder | qwen_3_4b_fp8_mixed.safetensors Qwen3 4B FP8 · Comfy-Org/z_image_turbo | models/text_encoders | 5.6 GB | Download → |
| VAE | flux2-vae.safetensors FLUX.2 VAE · Comfy-Org/flux2-dev | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 13.7 GB | |||
Alternatives: Qwen3 4B BF16 (8.0 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: FP8 workflow (.json). Drag the file into ComfyUI. All workflows →
Shared memory: about 19.7 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 FLUX.2 klein 4B file on 96 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · black-forest-labs | 7.8 GB | 9.6 GB | fits · 86.4 GB spare | the original weights | Hugging Face → |
| Q8_0 GGUF · unsloth | 4.3 GB | 6.1 GB | fits · 89.9 GB spare | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · black-forest-labs | 4.1 GB | 5.9 GB | fits · 90.1 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · unsloth | 3.4 GB | 5.2 GB | fits · 90.8 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · unsloth | 3.1 GB | 4.9 GB | fits · 91.1 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · unsloth | 2.6 GB | 4.4 GB | fits · 91.6 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · unsloth | 2.1 GB | 3.9 GB | fits · 92.1 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · unsloth | 1.8 GB | 3.6 GB | fits · 92.4 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 1 GB of working memory for FLUX.2 klein 4B and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run FLUX.2 klein 4B on a Radeon 8060S (Strix Halo) 96 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the Radeon 8060S (Strix Halo) 96 GB
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'.
96 GB LPDDR5X (shared system memory) · 256-bit · 256 GB/s · RDNA 3.5. Everything that runs on it →
05Questions
How much VRAM does FLUX.2 klein 4B need?
Around 3.6 GB with the smallest file (Q2_K) and 5.9 GB with an 8-bit file (FP8). The full 16-bit file needs about 9.6 GB.
Which FLUX.2 klein 4B file should I download for the Radeon 8060S (Strix Halo) 96 GB?
16-bit (7.8 GB) from black-forest-labs/FLUX.2-klein-4B.
FP8 or Q8_0 for FLUX.2 klein 4B on the Radeon 8060S (Strix Halo) 96 GB?
Q8_0 (4.3 GB). The Radeon 8060S (Strix Halo) 96 GB has no FP8 maths, so FP8 (4.1 GB) only saves memory and is a step further from the original.
How much do I need to download for FLUX.2 klein 4B on the Radeon 8060S (Strix Halo) 96 GB?
13.7 GB: flux-2-klein-4b.safetensors, qwen_3_4b_fp8_mixed.safetensors, flux2-vae.safetensors.