sraka 27b experimental needs about 19.0 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 5.9 GB (BF16) to 28.6 GB (Q8_0).
sraka 27b experimental is a 26.9B-parameter Qwen model in GGUF format, quantized by texdata. Its trained context length is 256K tokens. The repository has 4 quant files, from 5.9 GB (BF16) to 28.6 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 5.9 GB | 7.2 GB | Fits | Get file → | |
| Q4_K_M | 16.5 GB | 19.0 GB | Too big | Get file → | |
| Q5_K_M | 19.2 GB | 22.0 GB | Too big | Get file → | |
| Q8_0 | 28.6 GB | 32.5 GB | Too big | Get file → |
What GPU do you need for sraka 27b experimental?
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: the best quant that fits is BF16 (5.9 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (5.9 GB file, about 7.2 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (5.9 GB file, about 7.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 22.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 22.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 32.5 GB in use).
Which sraka 27b experimental quant should you choose?
Q4_K_M is the usual starting point for sraka 27b experimental: it balances file size and quality well. Here it is a 16.5 GB file.
The Q8_0 file is 28.6 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is BF16 at 5.9 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 sraka 27b experimental
How much VRAM does sraka 27b experimental need?
About 19.0 GB at Q4_K_M with an 8K context window. That is the 16.5 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 sraka 27b experimental on an 8 GB GPU?
Yes, with BF16: the 5.9 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of sraka 27b experimental GGUF?
It depends on the quant: BF16 is 5.9 GB, Q4_K_M is 16.5 GB, Q5_K_M is 19.2 GB, Q8_0 is 28.6 GB.
What context length does sraka 27b experimental support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download sraka 27b experimental GGUF?
The files are on Hugging Face in the texdata/sraka-27b-experimental repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does sraka 27b experimental use?
Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.