sakura 14b qwen2beta v0.9.2 IMX needs about 17.2 GB of memory at its main file (a 10.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 6.1 GB to 10.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.
sakura 14b qwen2beta v0.9.2 IMX is a 14.2B-parameter Qwen model in GGUF format, quantized by shing3232. Its trained context length is 32K tokens. The repository has 5 quant files, from 6.1 GB to 10.0 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 6.1 GB | 13.3 GB | Too big | Get file → | |
| — | 7.8 GB | 15.1 GB | Too big | Get file → | |
| — | 10.0 GB | 17.2 GB | Too big | Get file → | |
| — | 10.0 GB | 17.2 GB | Too big | Get file → | |
| — | 10.0 GB | 17.2 GB | Too big | Get file → |
What GPU do you need for sakura 14b qwen2beta v0.9.2 IMX?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: the best quant that fits is the main file (7.8 GB file, about 15.1 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (10.0 GB file, about 17.2 GB in use).
Which sakura 14b qwen2beta v0.9.2 IMX quant should you choose?
If memory is tight, the smallest file is the first one in the table at 6.1 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
Frequently asked questions about sakura 14b qwen2beta v0.9.2 IMX
How much VRAM does sakura 14b qwen2beta v0.9.2 IMX need?
About 17.2 GB at its main file with an 8K context window. That is the 10.0 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 sakura 14b qwen2beta v0.9.2 IMX on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of sakura 14b qwen2beta v0.9.2 IMX GGUF?
It depends on the quant: file is 6.1 GB, file is 7.8 GB, file is 10.0 GB, file is 10.0 GB, file is 10.0 GB.
What context length does sakura 14b qwen2beta v0.9.2 IMX support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 6.7 GB at 8K and 26.8 GB at 32K.
Where can I download sakura 14b qwen2beta v0.9.2 IMX GGUF?
The files are on Hugging Face in the shing3232/sakura-14b-qwen2beta-v0.9.2-IMX repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.