phi tuned lora needs about 0.6 GB of memory at BF16 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.
phi tuned lora is a 28M-parameter Phi model in GGUF format, quantized by bakch92. The repository has 1 quant file, from 0.1 GB (BF16) to 0.1 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 0.1 GB | 0.6 GB | Fits | Get file → |
What GPU do you need for phi tuned lora?
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 (0.1 GB file, about 0.6 GB in use).
Which phi tuned lora quant should you choose?
BF16 (0.1 GB) is the middle option in this repository. 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 phi tuned lora
How much VRAM does phi tuned lora need?
About 0.6 GB at BF16 with an 8K context window. That is the 0.1 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 phi tuned lora on an 8 GB GPU?
Yes, with BF16: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of phi tuned lora GGUF?
It depends on the quant: BF16 is 0.1 GB.
Where can I download phi tuned lora GGUF?
The files are on Hugging Face in the bakch92/phi-tuned_lora_gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.