StepFun 5 Preview needs about 405.0 GB of memory at Q4_K_M (a 361.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 0.9 GB (BF16) to 361.1 GB (Q4_K_M).
StepFun 5 Preview is a 436M-parameter Stepfun model in GGUF format, quantized by vcruz305. Its trained context length is 1024K tokens. The repository has 4 quant files, from 0.9 GB (BF16) to 361.1 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 0.9 GB | 1.5 GB | Fits | Get file → | |
| BF16 | 5.0 GB | 6.1 GB | Fits | Get file → | |
| IQ1_S | 119.5 GB (25 parts) | 134.4 GB | Too big | Get file → | |
| Q4_K_M | 361.1 GB (25 parts) | 405.0 GB | Too big | Get file → |
What GPU do you need for StepFun 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: the best quant that fits is BF16 (0.9 GB file, about 1.5 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (0.9 GB file, about 1.5 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (5.0 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (5.0 GB file, about 6.1 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (5.0 GB file, about 6.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (5.0 GB file, about 6.1 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (5.0 GB file, about 6.1 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (5.0 GB file, about 6.1 GB in use).
Which StepFun 5 Preview quant should you choose?
Q4_K_M is the usual starting point for StepFun 5 Preview: it balances file size and quality well. Here it is a 361.1 GB file.
If memory is tight, the smallest file is BF16 at 0.9 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about StepFun 5 Preview
How much VRAM does StepFun 5 Preview need?
About 405.0 GB at Q4_K_M with an 8K context window. That is the 361.1 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 StepFun 5 Preview on an 8 GB GPU?
Yes, with BF16: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of StepFun 5 Preview GGUF?
It depends on the quant: BF16 is 0.9 GB, BF16 is 5.0 GB, IQ1_S is 119.5 GB, Q4_K_M is 361.1 GB.
What context length does StepFun 5 Preview support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download StepFun 5 Preview GGUF?
The files are on Hugging Face in the vcruz305/StepFun-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 StepFun 5 Preview use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.