Instructions to use TheStageAI/gemma-4-12B-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TheStageAI/gemma-4-12B-it-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 TheStageAI/gemma-4-12B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheStageAI/gemma-4-12B-it-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 TheStageAI/gemma-4-12B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheStageAI/gemma-4-12B-it-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 TheStageAI/gemma-4-12B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheStageAI/gemma-4-12B-it-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 TheStageAI/gemma-4-12B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheStageAI/gemma-4-12B-it-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheStageAI/gemma-4-12B-it-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use TheStageAI/gemma-4-12B-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheStageAI/gemma-4-12B-it-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": "TheStageAI/gemma-4-12B-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheStageAI/gemma-4-12B-it-GGUF:Q4_K_M

Ollama
How to use TheStageAI/gemma-4-12B-it-GGUF with Ollama:
```
ollama run hf.co/TheStageAI/gemma-4-12B-it-GGUF:Q4_K_M
```
Unsloth Desktop

How to use TheStageAI/gemma-4-12B-it-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheStageAI/gemma-4-12B-it-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": "TheStageAI/gemma-4-12B-it-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TheStageAI/gemma-4-12B-it-GGUF with Docker Model Runner:
```
docker model run hf.co/TheStageAI/gemma-4-12B-it-GGUF:Q4_K_M
```

Lemonade

How to use TheStageAI/gemma-4-12B-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheStageAI/gemma-4-12B-it-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-12B-it-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use TheStageAI/gemma-4-12B-it-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 TheStageAI/gemma-4-12B-it-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 TheStageAI/gemma-4-12B-it-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TheStageAI/gemma-4-12B-it-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheStageAI/gemma-4-12B-it-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 "TheStageAI/gemma-4-12B-it-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"

michellemoorre commited on Jul 21

Commit

2c3699f

verified ·

1 Parent(s): e450d17

Update model cards and release artwork

Browse files

Files changed (5) hide show

README.md +2 -2
assets/cta-edge-lm-dark.svg +9 -23
assets/cta-edge-lm-light.svg +9 -23
assets/thestage-edge-models-header.png +2 -2
release-manifest.json +26 -4

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ tags:
 </p>
 <p align="center">
-  <a class="inline-block" href="https://github.com/TheStageAI/edge-lm"><img class="dark:hidden" src="./assets/cta-edge-lm-light.svg" width="145" height="42" alt="Explore edge-lm on GitHub"><img class="hidden dark:block" src="./assets/cta-edge-lm-dark.svg" width="145" height="42" alt="Explore edge-lm on GitHub"></a>&nbsp;
   <a class="inline-block" href="https://docs.thestage.ai/"><img class="dark:hidden" src="./assets/cta-docs-light.svg" width="120" height="42" alt="Read TheStageAI documentation"><img class="hidden dark:block" src="./assets/cta-docs-dark.svg" width="120" height="42" alt="Read TheStageAI documentation"></a>&nbsp;
   <a class="inline-block" href="https://app.thestage.ai/"><img class="dark:hidden" src="./assets/cta-platform-light.svg" width="146" height="42" alt="Open TheStageAI Platform"><img class="hidden dark:block" src="./assets/cta-platform-dark.svg" width="146" height="42" alt="Open TheStageAI Platform"></a>
 </p>
@@ -72,7 +72,7 @@ P / I means prompt-strict / instruction-strict. IFEval uses deterministic non-th
 <summary><b>Evaluation protocol</b></summary>
 - **IFEval:** 541 prompts, native chat template, `enable_thinking=false`, temperature 0.
-- **MMLU-Pro:** 12,032 questions, native chat template, `enable_thinking=true`, temperature 1, top-p 0.95, 32,768-token output limit.
 - The headline BF16 comparison uses instruction-strict IFEval; the raw scores are shown in the table.
 MMLU-Pro includes every row shown above, including the complete XS result.

 </p>
 <p align="center">
+  <a class="inline-block" href="https://github.com/TheStageAI/edge-lm"><img class="dark:hidden" src="./assets/cta-edge-lm-light.svg" width="146" height="42" alt="Explore edge-lm on GitHub"><img class="hidden dark:block" src="./assets/cta-edge-lm-dark.svg" width="146" height="42" alt="Explore edge-lm on GitHub"></a>&nbsp;
   <a class="inline-block" href="https://docs.thestage.ai/"><img class="dark:hidden" src="./assets/cta-docs-light.svg" width="120" height="42" alt="Read TheStageAI documentation"><img class="hidden dark:block" src="./assets/cta-docs-dark.svg" width="120" height="42" alt="Read TheStageAI documentation"></a>&nbsp;
   <a class="inline-block" href="https://app.thestage.ai/"><img class="dark:hidden" src="./assets/cta-platform-light.svg" width="146" height="42" alt="Open TheStageAI Platform"><img class="hidden dark:block" src="./assets/cta-platform-dark.svg" width="146" height="42" alt="Open TheStageAI Platform"></a>
 </p>
 <summary><b>Evaluation protocol</b></summary>
 - **IFEval:** 541 prompts, native chat template, `enable_thinking=false`, temperature 0.
+- **MMLU-Pro:** 12,032 questions, vLLM, 0-shot, native chat template `tiger_cot_v1`, `enable_thinking=true`; `temperature=1`, `top_p=0.95`, `top_k=64`, `min_p=0`, `presence_penalty=0`, `frequency_penalty=0`, `repetition_penalty=1`, `seed=42`; `max_model_len=20480`, `max_new_tokens=16384`; dataset revision `b189ec765aa7ed75c8acfea42df31fdae71f97be`.
 - The headline BF16 comparison uses instruction-strict IFEval; the raw scores are shown in the table.
 MMLU-Pro includes every row shown above, including the complete XS result.

assets/cta-edge-lm-dark.svg CHANGED Viewed

assets/cta-edge-lm-light.svg CHANGED Viewed

assets/thestage-edge-models-header.png CHANGED Viewed

Git LFS Details

SHA256: 7a92eef43d92f92bcb3156e74b11d007a86081c5818d78cb9a6b258cb2a1d8ed
Pointer size: 132 Bytes
Size of remote file: 1.04 MB

Git LFS Details

SHA256: 711ade8e4e2cecc8c1da11891be08470e2870b5d948e262b726a7c86a99cef2f
Pointer size: 131 Bytes
Size of remote file: 834 kB

release-manifest.json CHANGED Viewed

@@ -9,10 +9,32 @@
       "sample_count": 541
     },
     "mmlu_pro": {
-      "decoding": "temperature=1, top_p=0.95",
-      "mode": "native chat, enable_thinking=true",
       "protocol": "mmlu_pro_cardlike_thinking_v2",
-      "sample_count": 12032
     }
   },
   "bf16_reference": {
@@ -36,7 +58,7 @@
   },
   "display_name": "Gemma 4 12B IT",
   "family": "Gemma 4",
-  "generated_at": "2026-07-21T14:04:34.695994+00:00",
   "license": "apache-2.0",
   "model_key": "gemma4_12b",
   "reasoning_policy": {

       "sample_count": 541
     },
     "mmlu_pro": {
+      "backend": "vllm",
+      "dataset_revision": "b189ec765aa7ed75c8acfea42df31fdae71f97be",
+      "decoding": "temperature=1.0, top_p=0.95, top_k=64, min_p=0.0, presence_penalty=0.0, frequency_penalty=0.0, repetition_penalty=1.0, seed=42",
+      "enable_prefix_caching": false,
+      "enable_thinking": true,
+      "language_model_only": true,
+      "max_model_len": 20480,
+      "max_new_tokens": 16384,
+      "mode": "native_chat, enable_thinking=true",
+      "ntrain": 0,
+      "prompt_format": "native_chat",
+      "prompt_template_id": "tiger_cot_v1",
       "protocol": "mmlu_pro_cardlike_thinking_v2",
+      "sample_count": 12032,
+      "sampling": {
+        "frequency_penalty": 0.0,
+        "min_p": 0.0,
+        "presence_penalty": 0.0,
+        "repetition_penalty": 1.0,
+        "seed": 42,
+        "temperature": 1.0,
+        "top_k": 64,
+        "top_p": 0.95
+      },
+      "stop_sequences": [],
+      "system_prompt": null
     }
   },
   "bf16_reference": {
   },
   "display_name": "Gemma 4 12B IT",
   "family": "Gemma 4",
+  "generated_at": "2026-07-21T17:43:34.621255+00:00",
   "license": "apache-2.0",
   "model_key": "gemma4_12b",
   "reasoning_policy": {