Phi 3 Medium 4k Instruct needs about 13.6 GB of memory at Q6_K (a 11.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 9.6 GB (Q5_K_S) to 27.9 GB.
Phi 3 Medium 4k Instruct is a 14B-parameter Phi model in GGUF format, quantized by MaziyarPanahi. Its trained context length is 4K tokens. The repository has 5 quant files, from 9.6 GB (Q5_K_S) to 27.9 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_S | 9.6 GB | 11.0 GB | Too big | Get file → | |
| Q5_K_M | 9.9 GB | 11.2 GB | Too big | Get file → | |
| Q6_K | 11.5 GB | 12.8 GB | Too big | Get file → | |
| Q8_0 | 14.8 GB | 16.2 GB | Too big | Get file → | |
| — | 27.9 GB | 29.3 GB | Too big | Get file → |
What GPU do you need for Phi 3 Medium 4k Instruct?
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: the best quant that fits is Q5_K_S (9.6 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (11.5 GB file, about 13.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.8 GB file, about 17.0 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (27.9 GB file, about 30.1 GB in use).
Which Phi 3 Medium 4k Instruct quant should you choose?
Q6_K (11.5 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q5_K_S at 9.6 GB, with the quality trade-offs that come with fewer bits. 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 Phi 3 Medium 4k Instruct
How much VRAM does Phi 3 Medium 4k Instruct need?
About 13.6 GB at Q6_K with an 8K context window. That is the 11.5 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 Phi 3 Medium 4k Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Phi 3 Medium 4k Instruct GGUF?
It depends on the quant: Q5_K_S is 9.6 GB, Q5_K_M is 9.9 GB, Q6_K is 11.5 GB, Q8_0 is 14.8 GB, file is 27.9 GB.
What context length does Phi 3 Medium 4k Instruct support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.7 GB at 8K and 0.8 GB at 4K.
Where can I download Phi 3 Medium 4k Instruct GGUF?
The files are on Hugging Face in the MaziyarPanahi/Phi-3-medium-4k-instruct-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Phi 3 Medium 4k Instruct use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.