Instructions to use Baekpica/Motif-3-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 Baekpica/Motif-3-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 Baekpica/Motif-3-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf Baekpica/Motif-3-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Baekpica/Motif-3-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf Baekpica/Motif-3-GGUF:Q8_0

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 Baekpica/Motif-3-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Baekpica/Motif-3-GGUF:Q8_0

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 Baekpica/Motif-3-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Baekpica/Motif-3-GGUF:Q8_0

Use Docker

docker model run hf.co/Baekpica/Motif-3-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use Baekpica/Motif-3-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Baekpica/Motif-3-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": "Baekpica/Motif-3-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Baekpica/Motif-3-GGUF:Q8_0

Ollama
How to use Baekpica/Motif-3-GGUF with Ollama:
```
ollama run hf.co/Baekpica/Motif-3-GGUF:Q8_0
```

Unsloth Studio

How to use Baekpica/Motif-3-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Baekpica/Motif-3-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Baekpica/Motif-3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Baekpica/Motif-3-GGUF to start chatting

How to use Baekpica/Motif-3-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Baekpica/Motif-3-GGUF:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Baekpica/Motif-3-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Baekpica/Motif-3-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Baekpica/Motif-3-GGUF:Q8_0

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 "Baekpica/Motif-3-GGUF:Q8_0" \
  --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"

Docker Model Runner
How to use Baekpica/Motif-3-GGUF with Docker Model Runner:
```
docker model run hf.co/Baekpica/Motif-3-GGUF:Q8_0
```

Lemonade

How to use Baekpica/Motif-3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Baekpica/Motif-3-GGUF:Q8_0

Run and chat with the model

lemonade run user.Motif-3-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Baekpica/Motif-3-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 Baekpica/Motif-3-GGUF:Q8_0

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 Baekpica/Motif-3-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

Baekpica commited on 1 day ago

Commit

77c3d12

verified ·

1 Parent(s): 2cabbc9

Finalize H200 handoff documentation

Browse files

Files changed (2) hide show

.gitattributes +0 -1
README.md +15 -2

.gitattributes CHANGED Viewed

@@ -1,3 +1,2 @@
 *.gguf filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text


1	*.gguf filter=lfs diff=lfs merge=lfs -text
2	*.safetensors filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -37,6 +37,18 @@ Nothing is pruned, merged, expert-dropped, or layer-dropped.
 Start with `Motif-3-Q8_0-00001-of-00011.gguf`; split-aware runtimes discover
 the remaining shards automatically. Exact hashes are in `Q8_0-SHA256SUMS`.
 This reference follows the control-path protection policy used by the mixed
 release. Its 2,287 GGUF tensors comprise:
@@ -61,9 +73,10 @@ Q8_0; decision-sensitive controls remain at their locked higher precision.
 | GGUF tensors | 2,287 (51 fused gate/up tensors are losslessly separated) |
 | GGUF architecture | `motif3` |
 | Native context metadata | 262,144 tokens |
 | Official implementation oracle | `MotifTechnologies/vllm@4cd9eb4129883565e69d508038d783d59ee01867` |
 | Conversion base | `ggml-org/llama.cpp@1d2869c6e54d5003f3927a79efbca0fefa034a6d` |
-| Native runtime | [`Baekpica/ds4:feature/motif-3-model-loader@bbce7eec`](https://github.com/Baekpica/ds4/tree/feature/motif-3-model-loader) |
 | Public reproduction | [`Baekpica/motif-3-mixed-ds4`](https://github.com/Baekpica/motif-3-mixed-ds4) |
 | Private Spark handoff | Expensive state is preserved in `hf://buckets/Baekpica/motif-3-spark-handoff` |
@@ -110,7 +123,7 @@ GGUF runtime recognizes `motif3` merely because it can parse the container.
 The H200 development branch is publicly available as
 [`Baekpica/ds4:feature/motif-3-model-loader`](https://github.com/Baekpica/ds4/tree/feature/motif-3-model-loader)
 at exact implementation commit
-`bbce7eecf54703ae315328d4e240531c5a9f1a22`. The private Spark handoff also
 preserves an offline source snapshot and commit metadata.
 ## Intended use in the mixed-quant pipeline

 Start with `Motif-3-Q8_0-00001-of-00011.gguf`; split-aware runtimes discover
 the remaining shards automatically. Exact hashes are in `Q8_0-SHA256SUMS`.
+The weight files are fixed at Hub revision
+`5c266c95bf8c8d822d50e5e1cce9d108eaadb2af`. Later model-card commits do
+not change shard bytes or hashes.
+```bash
+hf download Baekpica/Motif-3-GGUF \
+  --revision 5c266c95bf8c8d822d50e5e1cce9d108eaadb2af \
+  --include 'Motif-3-Q8_0-*.gguf' \
+  --include Q8_0-SHA256SUMS \
+  --local-dir ./Motif-3-Q8_0
+```
 This reference follows the control-path protection policy used by the mixed
 release. Its 2,287 GGUF tensors comprise:
 | GGUF tensors | 2,287 (51 fused gate/up tensors are losslessly separated) |
 | GGUF architecture | `motif3` |
 | Native context metadata | 262,144 tokens |
+| Fixed Q8-weight revision | `5c266c95bf8c8d822d50e5e1cce9d108eaadb2af` |
 | Official implementation oracle | `MotifTechnologies/vllm@4cd9eb4129883565e69d508038d783d59ee01867` |
 | Conversion base | `ggml-org/llama.cpp@1d2869c6e54d5003f3927a79efbca0fefa034a6d` |
+| Native runtime | [`Baekpica/ds4:feature/motif-3-model-loader@d878ea1`](https://github.com/Baekpica/ds4/tree/feature/motif-3-model-loader) |
 | Public reproduction | [`Baekpica/motif-3-mixed-ds4`](https://github.com/Baekpica/motif-3-mixed-ds4) |
 | Private Spark handoff | Expensive state is preserved in `hf://buckets/Baekpica/motif-3-spark-handoff` |
 The H200 development branch is publicly available as
 [`Baekpica/ds4:feature/motif-3-model-loader`](https://github.com/Baekpica/ds4/tree/feature/motif-3-model-loader)
 at exact implementation commit
+`d878ea1a1d67bc0f0bd60e20e75b4a011aa2d8d9`. The private Spark handoff also
 preserves an offline source snapshot and commit metadata.
 ## Intended use in the mixed-quant pipeline