Step 3.7 Flash GGUF FineTune needs about 105.6 GB of memory at Q3_K_M (a 93.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 10 quants, from 0.5 GB to 394.0 GB (BF16).
Step 3.7 Flash GGUF FineTune is a 197B-parameter Step model in GGUF format, quantized by ashuaria. Its trained context length is 256K tokens. The repository has 10 quant files, from 0.5 GB to 394.0 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 1.0 GB | Fits | Get file → | |
| Q8_0 | 3.7 GB | 4.7 GB | Fits | Get file → | |
| BF16 | 7.0 GB | 8.3 GB | Too big | Get file → | |
| IQ3_XXS | 75.8 GB (2 parts) | 85.3 GB | Too big | Get file → | |
| Q3_K_M | 93.8 GB (3 parts) | 105.6 GB | Too big | Get file → | |
| Q3_K_L | 102.5 GB (3 parts) | 115.3 GB | Too big | Get file → | |
| IQ4_XS | 105.0 GB (3 parts) | 118.1 GB | Too big | Get file → | |
| Q4_K_S | 111.5 GB (3 parts) | 125.4 GB | Too big | Get file → | |
| Q8_0 | 209.4 GB (5 parts) | 235.0 GB | Too big | Get file → | |
| BF16 | 394.0 GB (9 parts) | 441.8 GB | Too big | Get file → |
What GPU do you need for Step 3.7 Flash GGUF FineTune?
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 the main file (0.5 GB file, about 1.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 4.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 4.7 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (7.0 GB file, about 8.3 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (7.0 GB file, about 8.3 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (7.0 GB file, about 8.3 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (7.0 GB file, about 8.3 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (7.0 GB file, about 8.3 GB in use).
Which Step 3.7 Flash GGUF FineTune quant should you choose?
Q3_K_M (93.8 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.
If memory is tight, the smallest file is the first one in the table at 0.5 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Step 3.7 Flash GGUF FineTune
How much VRAM does Step 3.7 Flash GGUF FineTune need?
About 105.6 GB at Q3_K_M with an 8K context window. That is the 93.8 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 3.7 Flash GGUF FineTune on an 8 GB GPU?
Yes, with Q8_0: the 3.7 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Step 3.7 Flash GGUF FineTune GGUF?
It depends on the quant: file is 0.5 GB, Q8_0 is 3.7 GB, BF16 is 7.0 GB, IQ3_XXS is 75.8 GB, Q3_K_M is 93.8 GB, Q3_K_L is 102.5 GB and 4 more.
What context length does Step 3.7 Flash GGUF FineTune support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download Step 3.7 Flash GGUF FineTune GGUF?
The files are on Hugging Face in the ashuaria/Step-3.7-Flash-GGUF-FineTune 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 3.7 Flash GGUF FineTune 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.