Step 5 Preview needs about 320.8 GB of memory at Q3_K_M (a 286.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds.
Step 5 Preview is a 601B-parameter Step model in GGUF format, quantized by SHSLab. Its trained context length is 1024K tokens. The repository has 1 quant file, from 286.0 GB (Q3_K_M) to 286.0 GB (Q3_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 286.0 GB (7 parts) | 320.8 GB | Too big | Get file → |
What GPU do you need for Step 5 Preview?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Step 5 Preview quant should you choose?
Q3_K_M (286.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Step 5 Preview
How much VRAM does Step 5 Preview need?
About 320.8 GB at Q3_K_M with an 8K context window. That is the 286.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Step 5 Preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 320.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Step 5 Preview GGUF?
It depends on the quant: Q3_K_M is 286.0 GB.
What context length does Step 5 Preview support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download Step 5 Preview GGUF?
The files are on Hugging Face in the SHSLab/Step-5-Preview-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Step 5 Preview use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.