phi4 needs about 11.1 GB of memory at Q4_K_M (a 8.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 15 quants, from 5.6 GB (Q2_K) to 29.3 GB (F16).
Phi-4: 14.7B llama-based model with 16K context
Phi-4 is a 14.7B parameter llama model trained on diverse data including synthetic textbook-like content. It supports 16384 context tokens and is released under the MIT license. The model is available in multiple GGUF quantizations.
Good at
- Large context handling
- Reasoning tasks
- Code generation
Limits
- No vision support
- Requires 8K context for memory estimates
- MIT license limits commercial use
Best for
- Chatbots needing long context
- Educational tutoring
- Code assistance
Who it’s for. Developers building conversational AI that requires extended context and reasoning. Researchers exploring large-context language models. Teams needing an open‑source, MIT‑licensed model for experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.6 GB | 7.8 GB | Tight | Get file → | |
| Q3_K_S | 6.5 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_M | 7.2 GB | 9.4 GB | Too big | Get file → | |
| Q3_K_L | 7.8 GB | 10.0 GB | Too big | Get file → | |
| Q4_0 | 8.4 GB | 10.6 GB | Too big | Get file → | |
| Q4_K_S | 8.4 GB | 10.6 GB | Too big | Get file → | |
| Q4_K_M | 8.9 GB | 11.1 GB | Too big | Get file → | |
| Q4_1 | 9.3 GB | 11.4 GB | Too big | Get file → | |
| Q5_0 | 10.2 GB | 12.3 GB | Too big | Get file → | |
| Q5_K_S | 10.2 GB | 12.3 GB | Too big | Get file → | |
| Q5_K_M | 10.4 GB | 12.6 GB | Too big | Get file → | |
| Q5_1 | 11.0 GB | 13.2 GB | Too big | Get file → | |
| Q6_K | 12.0 GB | 14.2 GB | Too big | Get file → | |
| Q8_0 | 15.6 GB | 17.8 GB | Too big | Get file → | |
| F16 | 29.3 GB | 31.5 GB | Too big | Get file → |
For 8‑10 GB VRAM, use Q4_K_M (est. 11.1 GB) or Q4_K_S (10.6 GB). For 12‑14 GB VRAM, Q5_K_M (12.6 GB) or Q5_0 (12.3 GB) are suitable. Higher precision Q6_K (14.2 GB) or Q8_0 (17.8 GB) need more memory.
What GPU do you need for phi4?
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 Q2_K (5.6 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_1 (9.3 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.0 GB file, about 14.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.6 GB file, about 17.8 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (29.3 GB file, about 31.5 GB in use).
Which phi4 quant should you choose?
Q4_K_M is the usual starting point for phi4: it balances file size and quality well. Here it is a 8.9 GB file.
The Q8_0 file is 15.6 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 5.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about phi4
How much VRAM does phi4 need?
About 11.1 GB at Q4_K_M with an 8K context window. That is the 8.9 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 phi4 on an 8 GB GPU?
Yes, with Q2_K: the 5.6 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of phi4 GGUF?
It depends on the quant: Q2_K is 5.6 GB, Q3_K_S is 6.5 GB, Q3_K_M is 7.2 GB, Q3_K_L is 7.8 GB, Q4_0 is 8.4 GB, Q4_K_S is 8.4 GB and 9 more.
What context length does phi4 support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.7 GB at 8K and 3.4 GB at 16K.
Where can I download phi4 GGUF?
The files are on Hugging Face in the calcuis/phi4 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does phi4 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.
Can I run Phi-4 on 8 GB VRAM?
Use Q4_K_S or Q4_K_M quantizations; they estimate 10.6 GB and 11.1 GB respectively, which may fit with some VRAM overhead.
Does Phi-4 support vision tasks?
No, Phi-4 is a text-only model and does not include vision capabilities.
What license applies to Phi-4?
Phi-4 is released under the MIT license, allowing free use and modification.