Phi 4 Reasoning 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 25 quants, from 4.7 GB (IQ2_S) to 29.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.7 GB.
Phi 4 Reasoning – 14.7B parameter model for coding and reasoning
Phi 4 Reasoning is a 14.7B parameter Phi family model built on the phi3 architecture. It is trained on math, science, coding, and reasoning data and supports a 32,768 token context window. The model is released under the MIT license.
Good at
- Coding tasks
- Complex reasoning
- Long chain‑of‑thought generation
Limits
- No vision support
- Requires 8,000 token context for memory estimates
- No mixture of experts
Best for
- Competitive coding contests
- Math olympiad problem solving
- Algorithmic reasoning
Who it’s for. Developers and researchers needing a large reasoning model for code and math. The model is suitable for applications that require long context and detailed chain‑of‑thought explanations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_S | 4.7 GB | 6.9 GB | Fits | Get file → | |
| IQ2_M | 5.1 GB | 7.3 GB | Tight | Get file → | |
| Q2_K | 5.5 GB | 7.7 GB | Tight | Get file → | |
| IQ3_XXS | 5.8 GB | 8.0 GB | Too big | Get file → | |
| Q2_K_L | 6.0 GB | 8.2 GB | Too big | Get file → | |
| IQ3_XS | 6.2 GB | 8.4 GB | Too big | Get file → | |
| Q3_K_S | 6.5 GB | 8.7 GB | Too big | Get file → | |
| IQ3_M | 6.9 GB | 9.1 GB | Too big | Get file → | |
| Q3_K_M | 7.4 GB | 9.5 GB | Too big | Get file → | |
| Q3_K_L | 7.9 GB | 10.1 GB | Too big | Get file → | |
| IQ4_XS | 7.9 GB | 10.1 GB | Too big | Get file → | |
| Q3_K_XL | 8.4 GB | 10.6 GB | Too big | Get file → | |
| IQ4_NL | 8.4 GB | 10.6 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 | 9.1 GB | 11.2 GB | Too big | Get file → | |
| Q4_1 | 9.3 GB | 11.4 GB | Too big | Get file → | |
| Q4_K_L | 9.4 GB | 11.6 GB | Too big | Get file → | |
| Q5_K_S | 10.2 GB | 12.3 GB | Too big | Get file → | |
| Q5_K_M | 10.6 GB | 12.8 GB | Too big | Get file → | |
| Q5_K_L | 10.9 GB | 13.1 GB | Too big | Get file → | |
| Q6_K | 12.0 GB | 14.2 GB | Too big | Get file → | |
| Q6_K_L | 12.3 GB | 14.5 GB | Too big | Get file → | |
| Q8_0 | 15.6 GB | 17.8 GB | Too big | Get file → | |
| BF16 | 29.3 GB | 31.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_S (4.73 GB) or IQ2_M (5.11 GB). For 12 GB VRAM, Q4_0 (8.41 GB) or Q4_K_S (8.44 GB) are good choices. For 24 GB VRAM, Q6_K (12.03 GB) or Q6_K_L (12.28 GB) provide higher quality. Memory estimates are approximate.
What GPU do you need for Phi 4 Reasoning?
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 IQ3_XXS (5.8 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_L (9.4 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K_L (12.3 GB file, about 14.5 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 BF16 (29.3 GB file, about 31.5 GB in use).
Which Phi 4 Reasoning quant should you choose?
Q4_K_M is the usual starting point for Phi 4 Reasoning: 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 IQ2_S at 4.7 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 4 Reasoning
How much VRAM does Phi 4 Reasoning 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 Reasoning on an 8 GB GPU?
Yes, with IQ3_XXS: the 5.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Phi 4 Reasoning GGUF?
It depends on the quant: IQ2_S is 4.7 GB, IQ2_M is 5.1 GB, Q2_K is 5.5 GB, IQ3_XXS is 5.8 GB, Q2_K_L is 6.0 GB, IQ3_XS is 6.2 GB and 19 more.
What context length does Phi 4 Reasoning support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.7 GB at 32K.
Where can I download Phi 4 Reasoning GGUF?
The files are on Hugging Face in the bartowski/microsoft_Phi-4-reasoning-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 Reasoning 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 Reasoning on 8 GB VRAM?
Yes, use the IQ2_S or IQ2_M quantization which are 4.73 GB and 5.11 GB respectively. The estimated VRAM usage at 8,000 context is 6.9 GB and 7.3 GB.
What context length does the model support?
The model supports up to 32,768 tokens, which is the trained context length.
Is the model licensed for commercial use?
The model is released under the MIT license, allowing commercial use.