PH

Phi-4-Mini-Reasoning

PhiGGUF by unslothUpdated 2025-05-01
Download on Hugging Face
Parameters3.84B
Context128K
Layers32
Architecturephi3
Smallest quant1.1 GB
Quick answer

Phi-4-Mini-Reasoning needs about 4.1 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.1 GB (IQ1_S) to 7.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Phi-4-mini-reasoning: compact math reasoning model

Phi-4-mini-reasoning is a lightweight open model built on synthetic data, fine‑tuned for advanced math reasoning. It supports a 128K token context length and is optimized for multi‑step, logic‑intensive problem solving in constrained environments.

Good at

  • Multi‑step math reasoning
  • Formal proof generation
  • Symbolic computation

Limits

  • No vision support
  • Designed only for math reasoning
  • Requires careful safety evaluation

Best for

  • Math tutoring applications
  • Automated proof assistants
  • Symbolic math problem solvers

Who it’s for. Developers building math‑centric tools who need a small, efficient model. The model is released under the MIT license and is suitable for research and production use where reasoning depth is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.1 GB 2.7 GB
Fits Get file →
IQ1_M1.2 GB 2.8 GB
Fits Get file →
IQ2_XXS1.3 GB 2.9 GB
Fits Get file →
IQ2_M1.5 GB 3.1 GB
Fits Get file →
IQ3_XXS1.7 GB 3.2 GB
Fits Get file →
Q2_K1.7 GB 3.3 GB
Fits Get file →
Q2_K_L1.7 GB 3.3 GB
Fits Get file →
Q2_K_XL1.7 GB 3.3 GB
Fits Get file →
Q3_K_S1.9 GB 3.5 GB
Fits Get file →
Q3_K_XL2.1 GB 3.7 GB
Fits Get file →
Q3_K_M2.1 GB 3.7 GB
Fits Get file →
IQ4_XS2.2 GB 3.8 GB
Fits Get file →
IQ4_NL2.3 GB 3.9 GB
Fits Get file →
Q4_02.3 GB 3.9 GB
Fits Get file →
Q4_K_XL2.5 GB 4.0 GB
Fits Get file →
Q4_K_M2.5 GB 4.1 GB
Fits Get file →
Q4_12.5 GB 4.1 GB
Fits Get file →
Q5_K_XL2.8 GB 4.4 GB
Fits Get file →
Q5_K_M2.8 GB 4.4 GB
Fits Get file →
Q6_K3.2 GB 4.7 GB
Fits Get file →
Q6_K_XL3.5 GB 5.1 GB
Fits Get file →
Q8_04.1 GB 5.7 GB
Fits Get file →
Q8_K_XL5.1 GB 6.7 GB
Fits Get file →
BF167.7 GB 9.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (≈2.7–2.8 GB memory at 8 k context). If 12 GB VRAM is available, Q4_K_M or Q4_K_XL (≈4.0–4.1 GB) provide higher quality. Larger quants such as Q6_K or Q8_0 exceed typical consumer GPU limits.

What GPU do you need for Phi-4-Mini-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: the best quant that fits is Q4_K_XL (2.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_K_XL (5.1 GB file, about 6.7 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.7 GB file, about 9.3 GB in use).

Which Phi-4-Mini-Reasoning quant should you choose?

Q4_K_M is the usual starting point for Phi-4-Mini-Reasoning: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.1 GB, about 1.6 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 IQ1_S at 1.1 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

Architecturephi3
Parameters3.84B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byunsloth
FamilyPhi
Licensemit
Downloads (HF)10,088
Last updated2025-05-01

Frequently asked questions about Phi-4-Mini-Reasoning

How much VRAM does Phi-4-Mini-Reasoning need?

About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.5 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-Reasoning on an 8 GB GPU?

Yes, with Q8_K_XL: the 5.1 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phi-4-Mini-Reasoning GGUF?

It depends on the quant: IQ1_S is 1.1 GB, IQ1_M is 1.2 GB, IQ2_XXS is 1.3 GB, IQ2_M is 1.5 GB, IQ3_XXS is 1.7 GB, Q2_K is 1.7 GB and 18 more.

What context length does Phi-4-Mini-Reasoning 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-Reasoning GGUF?

The files are on Hugging Face in the unsloth/Phi-4-mini-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-Mini-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-mini-reasoning on 8 GB VRAM?

Yes, with IQ1_S or IQ1_M quantization the model uses about 2.7–2.8 GB of VRAM at 8 k context.

Does the model support image inputs?

No, Phi-4-mini-reasoning is a text‑only model and has no vision capabilities.

What license applies to this model?

The model is released under the MIT license, allowing free use and modification.

Other GGUFs of Phi-4-mini-reasoning

Similar models

Browse all →

More from unsloth

All by unsloth →

More Phi models

All Phi →

Other small models

All small models →