phi 2 uncensored needs about 5.0 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 1.2 GB (Q2_K) to 5.6 GB.
Phi 2 uncensored – 2.78B parameter language model in GGUF format
Phi 2 uncensored is a 2.78 billion parameter model based on the phi2 architecture. It is available in multiple GGUF quantizations, ranging from Q2_K to Q8_0. The model supports a 2048‑token context window and is released under a non‑standard license.
Good at
- Fast inference on modest GPUs
- Compact quantized models
- Low‑latency text generation
Limits
- No vision or multimodal support
- Limited context length of 2048 tokens
- License not standard
Best for
- Rapid prototyping of text generation
- Running on edge devices with 8 GB VRAM
- Educational demonstrations of phi architecture
Who it’s for. Developers and researchers looking for a lightweight Phi‑based model for text‑only tasks. The model is suitable for environments where GPU memory is constrained and quick iteration is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.2 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 1.5 GB | 2.7 GB | Fits | Get file → | |
| Q4_K_M | 1.8 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.1 GB | 3.2 GB | Fits | Get file → | |
| Q6_K | 2.3 GB | 3.5 GB | Fits | Get file → | |
| Q8_0 | 3.0 GB | 4.1 GB | Fits | Get file → | |
| — | 5.6 GB | 6.7 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (1.79 GB) or Q5_K_M (2.07 GB) are suitable, using about 5–5.3 GB of VRAM at 8 k context. For 4 GB VRAM, Q2_K (1.17 GB) or Q3_K_M (1.48 GB) provide the best trade‑off. Larger models like Q8_0 (2.96 GB) need at least 6 GB VRAM.
What GPU do you need for phi 2 uncensored?
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 Q6_K (2.3 GB file, about 5.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (5.6 GB file, about 8.7 GB in use).
Which phi 2 uncensored quant should you choose?
Q4_K_M is the usual starting point for phi 2 uncensored: it balances file size and quality well. Here it is a 1.8 GB file.
The Q8_0 file is 3.0 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 Q2_K at 1.2 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 phi 2 uncensored
How much VRAM does phi 2 uncensored need?
About 5.0 GB at Q4_K_M with an 8K context window. That is the 1.8 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 phi 2 uncensored on an 8 GB GPU?
Yes, with Q8_0: the 3.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of phi 2 uncensored GGUF?
It depends on the quant: Q2_K is 1.2 GB, Q3_K_M is 1.5 GB, Q4_K_M is 1.8 GB, Q5_K_M is 2.1 GB, Q6_K is 2.3 GB, Q8_0 is 3.0 GB and 1 more.
What context length does phi 2 uncensored support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.
Where can I download phi 2 uncensored GGUF?
The files are on Hugging Face in the afrideva/phi-2-uncensored-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 2 uncensored use?
Hugging Face lists the license as other. 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 2 uncensored on 8 GB VRAM?
Yes, the Q4_K_M or Q5_K_M quantizations use approximately 5–5.3 GB of VRAM at 8 k context, fitting within an 8 GB GPU.
What is the context length of this model?
The model supports a maximum context length of 2048 tokens.
Does this model support vision tasks?
No, phi 2 uncensored is a text‑only model with no vision or multimodal capabilities.