Instructions to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp 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 jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp
# Run inference directly in the terminal:
llama cli -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp
# Run inference directly in the terminal:
llama cli -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

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 jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp
# Run inference directly in the terminal:
./llama-cli -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

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 jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

Use Docker

docker model run hf.co/jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

LM Studio
Jan

vLLM

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

Ollama
How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with Ollama:
```
ollama run hf.co/jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp
```

Unsloth Studio

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp 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 jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp 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 jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp to start chatting

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

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": "jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

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 "jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp" \
  --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 jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with Docker Model Runner:
```
docker model run hf.co/jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp
```

Lemonade

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

Run and chat with the model

lemonade run user.chadrock3.6-27b-coder-rocmfp4-mtp-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

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 jcbtc/chadrock3.6-27b-coder-rocmfp4-mtp

Run Hermes

hermes

Atomic Chat

jcbtc commited on Jun 23

Commit

f1f45cd

verified ·

1 Parent(s): f0d3910

Pin Chadrock v2 runner checkpoint fix

Browse files

Files changed (1) hide show

README.md +7 -3

README.md CHANGED Viewed

@@ -47,7 +47,7 @@ CHADROCK3.6 27B Coder is a Chadrock ROCmFP4/MTP GGUF release of the Qwopus3.6 27
 It uses the Qwopus3.6 27B Coder MTP line as upstream lineage, then converts that source into Charlie's AMD-focused ROCmFP4 Strix Lean runtime format. The public release name and artifact names are Chadrock names, while Qwopus stays explicit in lineage, base model metadata, and credits. The result is a compact 14 GB GGUF for local agentic coding, repository work, tool-use style prompts, and long-context experiments on unified-memory AMD hardware.
-This GGUF will **not run correctly with stock llama.cpp**. It needs the pinned [`ciru-ai/ROCmFPX`](https://github.com/ciru-ai/ROCmFPX/tree/be15a40d713f0818647739c68af95e9698d78e72) runner because the file uses ROCmFP4 tensor types that upstream llama.cpp does not currently understand.
 The model file is already provided here. You do **not** need to rebuild or quantize the model. Build the custom llama server once, download the files, and run the profile below.
@@ -143,7 +143,7 @@ For the pinned runner build, copy-paste build commands, request-level speculativ
 The current pinned runner build is:
 ```text
-ciru-ai/ROCmFPX commit: be15a40d713f0818647739c68af95e9698d78e72
 historical score tag: chadrock-rocmfp4-mtp-scores-20260621
 ```
@@ -189,6 +189,10 @@ GGML_HIP_ENABLE_UNIFIED_MEMORY=1 \
   -tb 32 \
   -ctk q4_0 \
   -ctv q4_0 \
   --spec-type draft-mtp \
   --spec-draft-device ROCm0 \
   --spec-draft-ngl all \
@@ -216,7 +220,7 @@ The projector is a GGUF-format projector file with a `.mmproj` repo extension so
 ```bash
 git clone https://github.com/ciru-ai/ROCmFPX.git
 cd ROCmFPX
-git checkout be15a40d713f0818647739c68af95e9698d78e72
 env JOBS=16 scripts/build-strix-rocmfp4-mtp.sh llama-server llama-bench
 ```

 It uses the Qwopus3.6 27B Coder MTP line as upstream lineage, then converts that source into Charlie's AMD-focused ROCmFP4 Strix Lean runtime format. The public release name and artifact names are Chadrock names, while Qwopus stays explicit in lineage, base model metadata, and credits. The result is a compact 14 GB GGUF for local agentic coding, repository work, tool-use style prompts, and long-context experiments on unified-memory AMD hardware.
+This GGUF will **not run correctly with stock llama.cpp**. It needs the pinned [`ciru-ai/ROCmFPX`](https://github.com/ciru-ai/ROCmFPX/tree/7aa484a2f0a504dc612a3d74a068024f3e6d6353) runner because the file uses ROCmFP4 tensor types that upstream llama.cpp does not currently understand.
 The model file is already provided here. You do **not** need to rebuild or quantize the model. Build the custom llama server once, download the files, and run the profile below.
 The current pinned runner build is:
 ```text
+ciru-ai/ROCmFPX commit: 7aa484a2f0a504dc612a3d74a068024f3e6d6353
 historical score tag: chadrock-rocmfp4-mtp-scores-20260621
 ```
   -tb 32 \
   -ctk q4_0 \
   -ctv q4_0 \
+  --ctx-checkpoints 0 \
+  --checkpoint-every-n-tokens -1 \
   --spec-type draft-mtp \
   --spec-draft-device ROCm0 \
   --spec-draft-ngl all \
 ```bash
 git clone https://github.com/ciru-ai/ROCmFPX.git
 cd ROCmFPX
+git checkout 7aa484a2f0a504dc612a3d74a068024f3e6d6353
 env JOBS=16 scripts/build-strix-rocmfp4-mtp.sh llama-server llama-bench
 ```