Instructions to use yhavinga/GLM-4.7-REAP-40p-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 yhavinga/GLM-4.7-REAP-40p-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 yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S
# Run inference directly in the terminal:
llama cli -hf yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S
# Run inference directly in the terminal:
llama cli -hf yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S

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 yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S
# Run inference directly in the terminal:
./llama-cli -hf yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S

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 yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S

Use Docker

docker model run hf.co/yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S

LM Studio
Jan
Ollama
How to use yhavinga/GLM-4.7-REAP-40p-GGUF with Ollama:
```
ollama run hf.co/yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S
```
Unsloth Desktop

How to use yhavinga/GLM-4.7-REAP-40p-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S

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": "yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use yhavinga/GLM-4.7-REAP-40p-GGUF with Docker Model Runner:
```
docker model run hf.co/yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S
```

Lemonade

How to use yhavinga/GLM-4.7-REAP-40p-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S

Run and chat with the model

lemonade run user.GLM-4.7-REAP-40p-GGUF-IQ3_S

List all available models

lemonade list

Hermes Agent

How to use yhavinga/GLM-4.7-REAP-40p-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 yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S

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 yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use yhavinga/GLM-4.7-REAP-40p-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S

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 "yhavinga/GLM-4.7-REAP-40p-GGUF:IQ3_S" \
  --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"

the gguf working but need to reduce the gpu layers

by gopi87 - opened Jan 4

Discussion

gopi87

Jan 4

hi the gguf working but need to reduce the gpu layers and increase the cpu layers while doing qunatation

@ubergarm any help for this ? this is looks promising btw.

yhavinga

Owner Jan 4

Deciding which layers go where sounds like it is configurable at inference / model loading time, right?

ubergarm

Jan 4

@yhavinga

Yes you can manually specify which layers go where.

I took only a very quick peek into the GGUFs and these look like mostly vanilla llama.cpp flavored mixtures? Already the attn/shexp/first N dense layers are quite small relative to the routed experts. In my own recipes I tend to keep those attn/shexp/first N dense layers larger and more heavily quantize the routed experts.

Ideally the attn/shexp/first N dense layers all fit into VRAM/GPU and only routed experts will run on the CPU/RAM for best speeds.

I'm curious how fast the REAP versions run here, as anecdotally I've heard REAP can run slower than the originals for some reason despite having much less weights. Also I have some full size versions that are smaller than this REAP version which would be interesting to compare perplexity. My smol-IQ1_KT can fit entirely on a 96GB VRAM for example and still runs okay haha...

Anyway cool to see so many options these days! Cheers!

matatrtatata

Jan 6

@ubergarm I would love to try your iq ks quants for this one. Did extensive python grinding
with Q6 and results are really good - @yhavinga thank you for that. Achieved around 3ts with all experts mlocked in ram in vanilla llama cpp. Maybe with ik4_ks we might get close to this results but with much better speed on ik_llama cpp?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment