Instructions to use mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF",
	filename="ReasoningCore-3B-Instruct-r01-Reflect-Math.IQ4_XS.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M

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 mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M

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 mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF with Ollama:
```
ollama run hf.co/mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M
```

Unsloth Studio new

How to use mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF to start chatting

Pi new

How to use mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M

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 mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ReasoningCore-3B-Instruct-r01-Reflect-Math-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on Mar 1, 2025

Commit

9e65eba

verified ·

1 Parent(s): 6cd72ab

uploaded from nico2

Browse files

@@ -33,3 +33,15 @@ 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
+ReasoningCore-3B-Instruct-r01-Reflect-Math.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+ReasoningCore-3B-Instruct-r01-Reflect-Math.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+ReasoningCore-3B-Instruct-r01-Reflect-Math.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+ReasoningCore-3B-Instruct-r01-Reflect-Math.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ReasoningCore-3B-Instruct-r01-Reflect-Math.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+ReasoningCore-3B-Instruct-r01-Reflect-Math.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ReasoningCore-3B-Instruct-r01-Reflect-Math.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+ReasoningCore-3B-Instruct-r01-Reflect-Math.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ReasoningCore-3B-Instruct-r01-Reflect-Math.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+ReasoningCore-3B-Instruct-r01-Reflect-Math.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+ReasoningCore-3B-Instruct-r01-Reflect-Math.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+ReasoningCore-3B-Instruct-r01-Reflect-Math.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:50651b43d620450f7779d017253e6879d2b74ea54f00a3eeaec2a328f485a144
+size 1840907424

+version https://git-lfs.github.com/spec/v1
+oid sha256:7703515d19506f1901d8177b2f98eafeee8422bf1eab1b7539832d53f7a3cd53
+size 1363936416

+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c390d288aa3c9aa4a8beb24ec8b3694527cea3e65e90b6fc797a1e2a8f4781
+size 1815348384

+version https://git-lfs.github.com/spec/v1
+oid sha256:796813a56936b5759d8178938500142e28fa3dc13f0883cbe8e3db7e3d8d44d8
+size 1687159968

+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a46b99dd4af24f1a84df66a9ef47289142db17b2c8319be9f22171dac4487c
+size 1542849696

+version https://git-lfs.github.com/spec/v1
+oid sha256:b27ce2e51b520f296a496cbf7daa1d25e1b1e7355a4832c727b1c3ee0e3978da
+size 2019378336

+version https://git-lfs.github.com/spec/v1
+oid sha256:089b9581dc4a0d0527e383a38ca88b7e2d3324785d73d3058ddc4f4438eaccc1
+size 1928201376

+version https://git-lfs.github.com/spec/v1
+oid sha256:d33e486d5eb3de585176d4cab5a0e1a0538b9e0f8a2618b343205af3704a49d2
+size 2322154656

+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ad9d95fd1fd0df0302e0f06fb9737e9bc096e1f6a9abb2ec081283fae57a30
+size 2269512864

+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0d4d58cd3dda2e6cf9af45042229c337c494e1a84a1bece2fab82d2d32cc29
+size 2643854496

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

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

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

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0310d3898a33a06c2c9d24106c0fda51c14a7affcdd490185007b4ad057ccb36
+size 3421899936

+version https://git-lfs.github.com/spec/v1
+oid sha256:947c7a6f8777c758b897a822504781959fc540161c76550839068cf0b8c92c8a
+size 6433688736