phi3 nl sql needs about 6.5 GB of memory at Q5_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 2.8 GB (Q5_K_M) to 7.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
phi3 nl sql is a 3.82B-parameter Phi model in GGUF format, quantized by whoami02. Its trained context length is 128K tokens. The repository has 2 quant files, from 2.8 GB (Q5_K_M) to 7.6 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 2.8 GB | 6.5 GB | Fits | Get file → | |
| F16 | 7.6 GB | 11.4 GB | Too big | Get file → |
What GPU do you need for phi3 nl sql?
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: the best quant that fits is Q5_K_M (2.8 GB file, about 6.5 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (7.6 GB file, about 11.4 GB in use).
Which phi3 nl sql quant should you choose?
Q5_K_M (2.8 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about phi3 nl sql
How much VRAM does phi3 nl sql need?
About 6.5 GB at Q5_K_M with an 8K context window. That is the 2.8 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 phi3 nl sql on an 8 GB GPU?
Yes, with Q5_K_M: the 2.8 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of phi3 nl sql GGUF?
It depends on the quant: Q5_K_M is 2.8 GB, F16 is 7.6 GB.
What context length does phi3 nl sql support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.
Where can I download phi3 nl sql GGUF?
The files are on Hugging Face in the whoami02/phi3-nl-sql-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.