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

Libraries

How to use mradermacher/TON-3B-Math-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/TON-3B-Math-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/TON-3B-Math-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 mradermacher/TON-3B-Math-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/TON-3B-Math-GGUF:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/mradermacher/TON-3B-Math-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/TON-3B-Math-GGUF with Ollama:
```
ollama run hf.co/mradermacher/TON-3B-Math-GGUF:Q4_K_M
```
Unsloth Desktop

How to use mradermacher/TON-3B-Math-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/TON-3B-Math-GGUF:Q4_K_M

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": "mradermacher/TON-3B-Math-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use mradermacher/TON-3B-Math-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/TON-3B-Math-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.TON-3B-Math-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mradermacher/TON-3B-Math-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 mradermacher/TON-3B-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/TON-3B-Math-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mradermacher/TON-3B-Math-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/TON-3B-Math-GGUF:Q4_K_M

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 "mradermacher/TON-3B-Math-GGUF:Q4_K_M" \
  --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"

mradermacher commited on May 22, 2025

Commit

bad74cf

verified ·

1 Parent(s): a481e7d

uploaded from nico1

Browse files

Files changed (13) hide show

.gitattributes +12 -0
TON-3B-Math.IQ4_XS.gguf +3 -0
TON-3B-Math.Q2_K.gguf +3 -0
TON-3B-Math.Q3_K_L.gguf +3 -0
TON-3B-Math.Q3_K_M.gguf +3 -0
TON-3B-Math.Q3_K_S.gguf +3 -0
TON-3B-Math.Q4_K_M.gguf +3 -0
TON-3B-Math.Q4_K_S.gguf +3 -0
TON-3B-Math.Q5_K_M.gguf +3 -0
TON-3B-Math.Q5_K_S.gguf +3 -0
TON-3B-Math.Q6_K.gguf +3 -0
TON-3B-Math.Q8_0.gguf +3 -0
TON-3B-Math.f16.gguf +3 -0

@@ -35,3 +35,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 TON-3B-Math.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 TON-3B-Math.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 TON-3B-Math.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 TON-3B-Math.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text
+TON-3B-Math.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+TON-3B-Math.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+TON-3B-Math.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+TON-3B-Math.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+TON-3B-Math.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+TON-3B-Math.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+TON-3B-Math.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+TON-3B-Math.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+TON-3B-Math.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+TON-3B-Math.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+TON-3B-Math.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+TON-3B-Math.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:53a6cd23f48ce697314f12936f4768c901af23bbd989d8647f5051a531aac590
+size 1918491456

+version https://git-lfs.github.com/spec/v1
+oid sha256:1917e931036b8b77a1ec9e2451c15f7d10ee7aa28131a9dc0a96aa940e7391b7
+size 1376856896

+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf6bbf09b1e5a09da4bce827561717ff4792d73af1e6591732d2ff27a979e3c
+size 1841095488

+version https://git-lfs.github.com/spec/v1
+oid sha256:b28c23e57914e028f4049faf1e445947193ed438ef6ba0f8d8d364179c638317
+size 1724179264

+version https://git-lfs.github.com/spec/v1
+oid sha256:f590165b1f2af4d4bdfa6dcb2e78f98cc6ca9e485371f5353afba9a565b13d91
+size 1588060992

+version https://git-lfs.github.com/spec/v1
+oid sha256:d814afc9d12deee14cfb0bf37f2b32512c044899d2e99f7dec490ccc0360dac3
+size 2104933184

+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e09fe66cdd5875aff26491bd7adbf43adc4e02664d821df0f79c2a735d9bbe
+size 2009414464

+version https://git-lfs.github.com/spec/v1
+oid sha256:b32a34d2cdbd1d3332270210e0808823681a686703e837ba9b54f8c6d9c814ee
+size 2438740800

+version https://git-lfs.github.com/spec/v1
+oid sha256:9fa7872f0bc1862f99f65fc6dadd22c8c5cc237e149094e15e94d1c0c31c1720
+size 2383592256

+version https://git-lfs.github.com/spec/v1
+oid sha256:2462513e6f5747c0605918a818ab85d412c8598e2c706f110e8ac1bb8b459b35
+size 2793411392

	@@ -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:b25b958c8872c94a85dc94f70894168ecaa45b28738bfae22fee6931487f3c96
+size 3616088896

+version https://git-lfs.github.com/spec/v1
+oid sha256:be6143fc70ccf025341927c5e0dd2526e7e9b60b5932a8467569503b73cf9eb3
+size 6800646976