Step5 Preview needs about 290.3 GB of memory at Q3_K_S (a 258.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 258.7 GB (Q3_K_S) to 286.0 GB (Q3_K_M).
Step5 Preview is a 601B-parameter Step model in GGUF format, quantized by avar6. Its trained context length is 1024K tokens. The repository has 2 quant files, from 258.7 GB (Q3_K_S) to 286.0 GB (Q3_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 258.7 GB | 290.3 GB | Too big | Get file → | |
| Q3_K_M | 286.0 GB (7 parts) | 320.8 GB | Too big | Get file → |
What GPU do you need for Step5 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 Step5 Preview quant should you choose?
Q3_K_S (258.7 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 Step5 Preview
How much VRAM does Step5 Preview need?
About 290.3 GB at Q3_K_S with an 8K context window. That is the 258.7 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 Step5 Preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 290.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Step5 Preview GGUF?
It depends on the quant: Q3_K_S is 258.7 GB, Q3_K_M is 286.0 GB.
What context length does Step5 Preview support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download Step5 Preview GGUF?
The files are on Hugging Face in the avar6/Step5-Preview repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.