Instructions to use stealth-model/missingno with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use stealth-model/missingno 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 stealth-model/missingno:IQ2_XXS
# Run inference directly in the terminal:
llama cli -hf stealth-model/missingno:IQ2_XXS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf stealth-model/missingno:IQ2_XXS
# Run inference directly in the terminal:
llama cli -hf stealth-model/missingno:IQ2_XXS

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf stealth-model/missingno:IQ2_XXS
# Run inference directly in the terminal:
./build/bin/llama cli -hf stealth-model/missingno:IQ2_XXS

Use Docker

docker model run hf.co/stealth-model/missingno:IQ2_XXS

Llama new
LM Studio
Jan

vLLM

How to use stealth-model/missingno with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/stealth-model/missingno:IQ2_XXS

Ollama
How to use stealth-model/missingno with Ollama:
```
ollama run hf.co/stealth-model/missingno:IQ2_XXS
```
Unsloth Desktop

How to use stealth-model/missingno with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf stealth-model/missingno:IQ2_XXS

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": "stealth-model/missingno:IQ2_XXS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use stealth-model/missingno with Docker Model Runner:
```
docker model run hf.co/stealth-model/missingno:IQ2_XXS
```

Lemonade

How to use stealth-model/missingno with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull stealth-model/missingno:IQ2_XXS

Run and chat with the model

lemonade run user.missingno-IQ2_XXS

List all available models

lemonade list

Hermes Agent

How to use stealth-model/missingno with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf stealth-model/missingno:IQ2_XXS

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 stealth-model/missingno:IQ2_XXS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use stealth-model/missingno with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf stealth-model/missingno:IQ2_XXS

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 "stealth-model/missingno:IQ2_XXS" \
  --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"

stealth-model commited on 1 day ago

Commit

e02bd0c

verified ·

1 Parent(s): 5602529

Update card: StealthMark 1.8.10, plainer links, softer panel backgrounds

Browse files

Files changed (4) hide show

README.md +9 -9
panels/case.webp +2 -2
panels/results.webp +2 -2
panels/verdict.webp +2 -2

README.md CHANGED Viewed

@@ -17,23 +17,23 @@ tags:
 thumbnail: https://stealthmodels.com/missingno/assets/social-card.png
 ---
-<a href="https://stealthmodels.com/missingno/?utm_source=huggingface&utm_medium=referral&utm_campaign=missingno-card"><img src="https://huggingface.co/stealth-model/missingno/resolve/main/panels/hero.webp" alt="MISSINGNO., the purple mystery jelly in a fake moustache, at a Nous Portal checkpoint."></a>
 **Our token counts matched MISSINGNO. to the tokenizer family behind Beam on all 24 phrases, five days before Reflection named it.**
-By [Stealth Models](https://stealthmodels.com/?utm_source=huggingface&utm_medium=referral&utm_campaign=missingno-card).
 StealthMark results for the released Beam 1.0:
-<a href="https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b?utm_source=huggingface&utm_medium=referral&utm_campaign=missingno-card"><img src="https://huggingface.co/stealth-model/missingno/resolve/main/panels/verdict.webp" alt="StealthMark 1.8.8 results for the released Beam 1.0: benchmark score 31.9 out of 100, General Intelligence 30.9, Visual Intelligence 33.8. Beam, the model behind MISSINGNO., is strongest at composing a whole scene: 52.4 on Beach."></a>
-<a href="https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b?utm_source=huggingface&utm_medium=referral&utm_campaign=missingno-card"><img src="https://huggingface.co/stealth-model/missingno/resolve/main/panels/results.webp" alt="Every StealthMark result of the released Beam 1.0: Beach 52.4, Foresight 49.4, Raccoon 46.3, Selfie 45.4, Latch 37.3, Ground Truth 27.9, Newton's Mirror 21.7, Mona Lisa 0.7."></a>
-[See the token-count test](https://stealthmodels.com/missingno?utm_source=huggingface&utm_medium=referral&utm_campaign=missingno-card#tokenizer)
-<a href="https://stealthmodels.com/missingno/?utm_source=huggingface&utm_medium=referral&utm_campaign=missingno-card"><img src="https://huggingface.co/stealth-model/missingno/resolve/main/panels/case.webp" alt="The case file. First seen 10 Oct 2026, revealed 16 Oct 2026, developer Reflection AI, context 262,144 tokens, input Text, tool calls Yes, including parallel calls, speed in our tests about 846 tok/s. 11 Oct 2026, our finding: Our token-count test matches all 24 phrases to the tokenizer family Beam turned out to use. 15 Oct 2026, our finding: The Cat Jam preview matches the same 24 counts in our test. 16 Oct 2026: Reflection releases Beam 1.0 with open weights and credits the MissingNo demo to it."></a>
-[Compare Beam with MiMo-V2.6-Pro, whose tokenizer it shares](https://stealthmodels.com/compare/beam-1.0-501b-a23b-vs-mimo-v2.6-pro?utm_source=huggingface&utm_medium=referral&utm_campaign=missingno-card)
 <details><summary>Facts as text</summary>
@@ -51,7 +51,7 @@ StealthMark results for the released Beam 1.0:
 </details>
 ## Run it
-MissingNo was Beam 1.0, which is open under Apache 2.0 at [reflection/Beam-1.0-501B-A23B](https://huggingface.co/reflection/Beam-1.0-501B-A23B). Its GGUF files are right here.
 | File | Size | Best for |
 |---|---|---|
@@ -68,5 +68,5 @@ llama-server \
 `--n-cpu-moe 52` keeps all 52 expert layers in system RAM. Lower it until your GPU is full. On a 192 GB Mac, leave it out.
 ---
-[Model guide](https://stealthmodels.com/missingno/?utm_source=huggingface&utm_medium=referral&utm_campaign=missingno-card) · [StealthMark leaderboard](https://huggingface.co/spaces/stealth-model/stealthmark) · [Follow us](https://huggingface.co/stealth-model)<br>
 Text and images: CC BY 4.0, stealthmodels.com.

 thumbnail: https://stealthmodels.com/missingno/assets/social-card.png
 ---
+<img src="https://huggingface.co/stealth-model/missingno/resolve/main/panels/hero.webp" alt="MISSINGNO., the purple mystery jelly in a fake moustache, at a Nous Portal checkpoint.">
 **Our token counts matched MISSINGNO. to the tokenizer family behind Beam on all 24 phrases, five days before Reflection named it.**
+By [Stealth Models](https://stealthmodels.com/).
 StealthMark results for the released Beam 1.0:
+<img src="https://huggingface.co/stealth-model/missingno/resolve/main/panels/verdict.webp" alt="StealthMark 1.8.10 results for the released Beam 1.0: benchmark score 31.9, General Intelligence 30.9, Visual Intelligence 33.8. Beam, the model behind MISSINGNO., is strongest at composing a whole scene: 52.4 on Beach.">
+<img src="https://huggingface.co/stealth-model/missingno/resolve/main/panels/results.webp" alt="Every StealthMark result of the released Beam 1.0: Beach 52.4, Foresight 49.4, Raccoon 46.3, Selfie 45.4, Latch 37.3, Ground Truth 27.9, Newton's Mirror 21.7, Mona Lisa 0.7.">
+[See the token-count test](https://stealthmodels.com/missingno#tokenizer)
+<img src="https://huggingface.co/stealth-model/missingno/resolve/main/panels/case.webp" alt="The case file. First seen 10 Oct 2026, revealed 16 Oct 2026, developer Reflection AI, context 262,144 tokens, input Text, tool calls Yes, including parallel calls, speed in our tests about 846 tok/s. 11 Oct 2026, our finding: Our token-count test matches all 24 phrases to the tokenizer family Beam turned out to use. 15 Oct 2026, our finding: The Cat Jam preview matches the same 24 counts in our test. 16 Oct 2026: Reflection releases Beam 1.0 with open weights and credits the MissingNo demo to it.">
+[Compare Beam with MiMo-V2.6-Pro, whose tokenizer it shares](https://stealthmodels.com/compare/beam-1.0-501b-a23b-vs-mimo-v2.6-pro)
 <details><summary>Facts as text</summary>
 </details>
 ## Run it
+MissingNo was Beam 1.0, which is open under Apache 2.0 at [reflection/Beam-1.0-501B-A23B](https://huggingface.co/reflection/Beam-1.0-501B-A23B). Its GGUF files are here.
 | File | Size | Best for |
 |---|---|---|
 `--n-cpu-moe 52` keeps all 52 expert layers in system RAM. Lower it until your GPU is full. On a 192 GB Mac, leave it out.
 ---
+[StealthMark leaderboard](https://huggingface.co/spaces/stealth-model/stealthmark)<br>
 Text and images: CC BY 4.0, stealthmodels.com.