Instructions to use StarFighter12/GLM-Steam-106B-A12B-v1-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 StarFighter12/GLM-Steam-106B-A12B-v1-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 StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K

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 StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K

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 StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K

Use Docker

docker model run hf.co/StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use StarFighter12/GLM-Steam-106B-A12B-v1-GGUF with Ollama:
```
ollama run hf.co/StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K
```
Unsloth Desktop

How to use StarFighter12/GLM-Steam-106B-A12B-v1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K

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": "StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use StarFighter12/GLM-Steam-106B-A12B-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K
```

Lemonade

How to use StarFighter12/GLM-Steam-106B-A12B-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K

Run and chat with the model

lemonade run user.GLM-Steam-106B-A12B-v1-GGUF-Q2_K

List all available models

lemonade list

Hermes Agent

How to use StarFighter12/GLM-Steam-106B-A12B-v1-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 StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K

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 StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use StarFighter12/GLM-Steam-106B-A12B-v1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K

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 "StarFighter12/GLM-Steam-106B-A12B-v1-GGUF:Q2_K" \
  --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"

TheDrummer's GLM Steam quantized using ik_llama.cpp

first attempt at quantizing something "on my own"

ive tried using both bartowski's and mradermacher's imatrix files but wasn't able to use any of them and had to make one myself from the guide (skill issue)

this quant requires ik_llama.cpp fork to work properly

followed ubergarm's quant cookers basic guide but since i had no idea what i was doing i just copied his recipes and applied it on TheDrummer's model

also used general calibration data instead of rp focused so performance may suffer a bit

feel free to roast me if i messed something up (which i certainly did)

Downloads last month: 29

GGUF

Model size

110B params

Architecture

glm4moe

Hardware compatibility

2-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for StarFighter12/GLM-Steam-106B-A12B-v1-GGUF

Base model

zai-org/GLM-4.5-Air

Finetuned

TheDrummer/GLM-Steam-106B-A12B-v1

Quantized

(11)

this model