lora model repo needs about 4.3 GB of memory at Q8_0 (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU.
lora model repo is a 3.21B-parameter Lora model in GGUF format, quantized by Ebonica. Its trained context length is 128K tokens. The repository has 1 quant file, from 3.4 GB (Q8_0) to 3.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 3.4 GB | 4.3 GB | Fits | Get file → |
What GPU do you need for lora model repo?
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: the best quant that fits is Q8_0 (3.4 GB file, about 4.3 GB in use).
Which lora model repo quant should you choose?
Q8_0 (3.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about lora model repo
How much VRAM does lora model repo need?
About 4.3 GB at Q8_0 with an 8K context window. That is the 3.4 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 lora model repo on an 8 GB GPU?
Yes, with Q8_0: the 3.4 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of lora model repo GGUF?
It depends on the quant: Q8_0 is 3.4 GB.
What context length does lora model repo support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download lora model repo GGUF?
The files are on Hugging Face in the Ebonica/lora_model_repo repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.