Instructions to use unsloth/Phi-4-mini-reasoning-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Phi-4-mini-reasoning-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="unsloth/Phi-4-mini-reasoning-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/Phi-4-mini-reasoning-GGUF")
model = AutoModelForCausalLM.from_pretrained("unsloth/Phi-4-mini-reasoning-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/Phi-4-mini-reasoning-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/Phi-4-mini-reasoning-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Phi-4-mini-reasoning-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Phi-4-mini-reasoning-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/Phi-4-mini-reasoning-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "unsloth/Phi-4-mini-reasoning-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Phi-4-mini-reasoning-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "unsloth/Phi-4-mini-reasoning-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Phi-4-mini-reasoning-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/Phi-4-mini-reasoning-GGUF with Ollama:
```
ollama run hf.co/unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL
```
Unsloth Desktop

How to use unsloth/Phi-4-mini-reasoning-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use unsloth/Phi-4-mini-reasoning-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Phi-4-mini-reasoning-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Phi-4-mini-reasoning-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use unsloth/Phi-4-mini-reasoning-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use unsloth/Phi-4-mini-reasoning-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "unsloth/Phi-4-mini-reasoning-GGUF:UD-Q4_K_XL" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

danielhanchen commited on May 1, 2025

Commit

632e8e4

verified ·

1 Parent(s): 20540d0

Add files using upload-large-folder tool

Browse files

Files changed (9) hide show

.gitattributes +6 -0
Phi-4-mini-reasoning-UD-IQ1_M.gguf +3 -0
Phi-4-mini-reasoning-UD-IQ1_S.gguf +3 -0
Phi-4-mini-reasoning-UD-IQ2_M.gguf +3 -0
Phi-4-mini-reasoning-UD-IQ3_XXS.gguf +3 -0
Phi-4-mini-reasoning-UD-Q2_K_XL.gguf +3 -0
Phi-4-mini-reasoning-UD-Q4_K_XL.gguf +3 -0
README.md +1 -40
config.json +139 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-UD-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-UD-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-UD-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-UD-Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-UD-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text

Phi-4-mini-reasoning-UD-IQ1_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8aeacce133f4e28ab19b607cd9d85edf9fb52dd231b866b903739b19372e1c37
+size 1195260832

Phi-4-mini-reasoning-UD-IQ1_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:325758ced3f234b5debfab7b97b040545f018438fb201ba670a1127d7a75e927
+size 1141193632

Phi-4-mini-reasoning-UD-IQ2_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fa80f2d71bf5e9356c9983d1ac092800ef8e458d5530ec4ce9d906af9a94b4d8
+size 1536129952

Phi-4-mini-reasoning-UD-IQ3_XXS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:be0af7b40c9cebc18e93adf26645aedadd542ea569ffadd96c3d7576576e5df9
+size 1668545440

Phi-4-mini-reasoning-UD-Q2_K_XL.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:795d18656943be4f9bdeddcde99bc7a3ea6f8c42acf66c3330e5036f9defa4ca
+size 1720237984

Phi-4-mini-reasoning-UD-Q4_K_XL.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:60fd722999c9c67dcf0d9f1b2aad550cbc8aa38c728eddbb0d94af8a016af581
+size 2462678944

README.md CHANGED Viewed

@@ -12,52 +12,13 @@ tags:
 - unsloth
 - math
 - code
-- phi
-- phi4
 widget:
 - messages:
   - role: user
     content: How to solve 3*x^2+4*x+5=1?
 ---
-> [!NOTE]
-> This Phi-4-mini-reasoning upload also includes our [Phi-4 bug fixes](https://unsloth.ai/blog/phi4).
->
-<div>
-  <p style="margin-bottom: 0; margin-top: 0;">
-    <strong>See <a href="https://huggingface.co/collections/unsloth/phi-4-all-versions-677eecf93784e61afe762afa">our collection</a> for all versions of Phi-4 including GGUF, 4-bit & 16-bit formats.</strong>
-  </p>
-<p style="margin-top: 0;margin-bottom: 0;">
-    <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
-  </p>
-  <div style="display: flex; gap: 5px; align-items: center; ">
-    <a href="https://github.com/unslothai/unsloth/">
-      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
-    </a>
-    <a href="https://discord.gg/unsloth">
-      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
-    </a>
-    <a href="https://docs.unsloth.ai/">
-      <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
-    </a>
-  </div>
-<h1 style="margin-top: 0rem;">✨ Run & Fine-tune Phi-4 with Unsloth!</h1>
-</div>
-- Fine-tune Phi-4 (14B) for free using our Google [Colab notebook here](https://docs.unsloth.ai/get-started/unsloth-notebooks)!
-- Read our Blog about Phi-4 support with our bug fixes: [unsloth.ai/blog/phi4](https://unsloth.ai/blog/phi4)
-- View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks).
-- Run & export your fine-tuned model to Ollama, llama.cpp or HF.
-| Unsloth supports          |    Free Notebooks                                                                                           | Performance | Memory use |
-|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
-| **Phi-4 (14B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4-Conversational.ipynb)               | 2x faster | 50% less |
-| **Qwen3 (14B)**      | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks)               | 3x faster | 70% less |
-| **GRPO with Qwen3 (8B)**      | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks)               | 3x faster | 80% less |
-| **Llama-3.2 (3B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb)               | 2.4x faster | 58% less |
-| **Llama-3.2 (11B vision)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb)               | 2x faster | 60% less |
-| **Qwen2.5 (7B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-Alpaca.ipynb)               | 2x faster | 60% less |
-## Phi-4-mini-reasoning
 Phi-4-mini-reasoning is a lightweight open model built upon synthetic data with a focus on high-quality, reasoning dense data further finetuned for more advanced math reasoning capabilities.
 The model belongs to the Phi-4 model family and supports 128K token context length.

 - unsloth
 - math
 - code
 widget:
 - messages:
   - role: user
     content: How to solve 3*x^2+4*x+5=1?
 ---
+## Model Summary
 Phi-4-mini-reasoning is a lightweight open model built upon synthetic data with a focus on high-quality, reasoning dense data further finetuned for more advanced math reasoning capabilities.
 The model belongs to the Phi-4 model family and supports 128K token context length.

config.json ADDED Viewed

	@@ -0,0 +1,139 @@

+{
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 199999,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 199999,
+  "full_attn_mod": 1,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "interpolate_factor": 1,
+  "lm_head_bias": false,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "phi3",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 200018,
+  "partial_rotary_factor": 0.75,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1,
+      1.118320672,
+      1.250641126,
+      1.398617824,
+      1.564103225,
+      1.74916897,
+      1.956131817,
+      2.187582649,
+      2.446418898,
+      2.735880826,
+      3.059592084,
+      3.421605075,
+      3.826451687,
+      4.279200023,
+      4.785517845,
+      5.351743533,
+      5.984965424,
+      6.693110555,
+      7.485043894,
+      8.370679318,
+      9.36110372,
+      10.4687158,
+      11.70738129,
+      13.09260651,
+      14.64173252,
+      16.37415215,
+      18.31155283,
+      20.47818807,
+      22.90118105,
+      25.61086418,
+      28.64115884,
+      32.03,
+      32.1,
+      32.13,
+      32.23,
+      32.6,
+      32.61,
+      32.64,
+      32.66,
+      32.7,
+      32.71,
+      32.93,
+      32.97,
+      33.28,
+      33.49,
+      33.5,
+      44.16,
+      47.77
+    ],
+    "short_factor": [
+      1,
+      1.118320672,
+      1.250641126,
+      1.398617824,
+      1.564103225,
+      1.74916897,
+      1.956131817,
+      2.187582649,
+      2.446418898,
+      2.735880826,
+      3.059592084,
+      3.421605075,
+      3.826451687,
+      4.279200023,
+      4.785517845,
+      5.351743533,
+      5.984965424,
+      6.693110555,
+      7.485043894,
+      8.370679318,
+      9.36110372,
+      10.4687158,
+      11.70738129,
+      13.09260651,
+      14.64173252,
+      16.37415215,
+      18.31155283,
+      20.47818807,
+      22.90118105,
+      25.61086418,
+      28.64115884,
+      32.03,
+      32.1,
+      32.13,
+      32.23,
+      32.6,
+      32.61,
+      32.64,
+      32.66,
+      32.7,
+      32.71,
+      32.93,
+      32.97,
+      33.28,
+      33.49,
+      33.5,
+      44.16,
+      47.77
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 200064
+}