phi 4 needs about 11.2 GB of memory at Q4_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 7.9 GB (Q3_K_L) to 15.6 GB (Q8_0).
Phi‑4: 15 B parameter LLM focused on coding and reasoning
Phi‑4 is a 15 billion parameter model built on the phi3 architecture. It supports a 16k token context length and is trained on 9.8 trillion tokens from diverse public, academic, and synthetic sources. The model is released under the MIT license and is available in multiple GGUF quantizations.
Good at
- Coding tasks
- Reasoning with long context
- Educational content generation
Limits
- No vision support
- Requires 8k+ context for full performance
- MIT license limits commercial use without attribution
Best for
- Developers building code assistants
- Educators creating math and science content
- Researchers testing long‑context reasoning
Who it’s for. The model is suitable for developers, educators, and researchers who need a reasonably sized LLM with strong coding and reasoning capabilities. It is ideal for those who can run it locally with a GPU that supports the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 7.9 GB | 10.1 GB | Too big | Get file → | |
| Q4_K_M | 9.1 GB | 11.2 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 → |
For 8 GB VRAM use Q3_K_L (≈10.1 GB memory at 8k context). For 12 GB VRAM use Q4_K_M (≈11.2 GB). For 16 GB VRAM use Q6_K (≈14.2 GB). The Q8_0 quantization needs about 17.8 GB memory and is best for the largest GPUs.
What GPU do you need for phi 4?
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 Q4_K_M (9.1 GB file, about 11.2 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).
Which phi 4 quant should you choose?
Q4_K_M is the usual starting point for phi 4: it balances file size and quality well. Here it is a 9.1 GB file.
The Q8_0 file is 15.6 GB, about 1.7 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 Q3_K_L at 7.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about phi 4
How much VRAM does phi 4 need?
About 11.2 GB at Q4_K_M with an 8K context window. That is the 9.1 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 4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of phi 4 GGUF?
It depends on the quant: Q3_K_L is 7.9 GB, Q4_K_M is 9.1 GB, Q6_K is 12.0 GB, Q8_0 is 15.6 GB.
What context length does phi 4 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 phi 4 GGUF?
The files are on Hugging Face in the lmstudio-community/phi-4-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 4 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?
Yes, using the Q3_K_L quantization which requires roughly 10.1 GB of VRAM at 8k context.
Does Phi‑4 support image input?
No, Phi‑4 does not have vision capabilities.
What license applies to Phi‑4?
Phi‑4 is released under the MIT license, allowing free use with attribution.