phi-4-mini needs about 4.7 GB of memory at Q6_K (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.6 GB (Q4_K_L) to 4.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Phi‑4‑mini, 3.84B parameter instruction model
Phi‑4‑mini is a 3.84B parameter instruction model based on the phi3 architecture. It supports tool usage and is released under the MIT license. The model was trained with a context length of 131072 tokens.
Good at
- Tool‑based instruction following
- Low‑latency inference on modest GPUs
- Compact 3.8B parameter size
Limits
- No vision support
- Requires 8‑k context for memory estimates
- No mixture of experts
Best for
- Chatbots needing quick responses
- Embedded systems with limited VRAM
- Rapid prototyping of instruction models
Who it’s for. Developers and researchers who need a lightweight instruction model with tool support. The model is suitable for projects that require a small footprint and fast inference on consumer hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_L | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q6_K | 3.2 GB | 4.7 GB | Fits | Get file → | |
| — | 4.1 GB | 5.7 GB | Fits | Get file → |
For 8‑GB VRAM, use the Q4_K_L quantized file (2.64 GB, ~4.2 GB memory at 8‑k context). If more memory is available, the Q6_K file (3.16 GB, ~4.7 GB memory) offers higher precision. The unknown quant file is larger and not recommended for low‑memory setups.
What GPU do you need for phi-4-mini?
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: the best quant that fits is the main file (4.1 GB file, about 5.7 GB in use).
Which phi-4-mini quant should you choose?
Q6_K (3.2 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 Q4_K_L at 2.6 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about phi-4-mini
How much VRAM does phi-4-mini need?
About 4.7 GB at Q6_K with an 8K context window. That is the 3.2 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-mini on an 8 GB GPU?
Yes, with the smaller files: the 4.1 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of phi-4-mini GGUF?
It depends on the quant: Q4_K_L is 2.6 GB, Q6_K is 3.2 GB, file is 4.1 GB.
What context length does phi-4-mini support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download phi-4-mini GGUF?
The files are on Hugging Face in the EasierAI/Phi-4-Mini-3.8B 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-mini 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‑mini on 8 GB VRAM?
Yes, the Q4_K_L quantized model uses about 4.2 GB of VRAM at 8‑k context, fitting within an 8‑GB GPU.
Does Phi‑4‑mini support vision tasks?
No, the model does not include vision capabilities.
What license applies to Phi‑4‑mini?
The model is released under the MIT license, allowing free use and modification.