Instructions to use jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus",
	filename="Step-3.7-Flash-ROCmFPX-Q3-QualityPlus-00001-of-00009.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus 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/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus
# Run inference directly in the terminal:
llama cli -hf jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus
# Run inference directly in the terminal:
llama cli -hf jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus

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/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus
# Run inference directly in the terminal:
./llama-cli -hf jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus

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/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus

Use Docker

docker model run hf.co/jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus

LM Studio
Jan

vLLM

How to use jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus"
# 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/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus

Ollama
How to use jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus with Ollama:
```
ollama run hf.co/jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus
```

Unsloth Studio

How to use jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus 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/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus 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/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus to start chatting

How to use jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus

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/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus 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/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus

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/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus

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/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus" \
  --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/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus with Docker Model Runner:
```
docker model run hf.co/jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus
```

Lemonade

How to use jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus

Run and chat with the model

lemonade run user.Step-3.7-Flash-ROCmFPX-Q3-QualityPlus-{{QUANT_TAG}}

List all available models

lemonade list

jcbtc commited on 8 days ago

Commit

dce6ec4

verified ·

1 Parent(s): edca42f

Add model card

Browse files

Files changed (1) hide show

README.md +30 -1

README.md CHANGED Viewed

@@ -147,7 +147,11 @@ Step-3.7-Flash-ROCmFPX-Q3-QualityPlus-00008-of-00009.gguf
 Step-3.7-Flash-ROCmFPX-Q3-QualityPlus-00009-of-00009.gguf
 ```
-The Step MTP draft model is not duplicated here. Use the Q8 draft from [`notSnix/Step-3.7-Flash-MTP-Draft-GGUF`](https://huggingface.co/notSnix/Step-3.7-Flash-MTP-Draft-GGUF), for example `Step-3.7-Flash-MTP-Q8_0.gguf`.
 This repo also includes the tested chat/tool template:
@@ -223,6 +227,7 @@ context: up to 262144
 slots: 1
 backend: Vulkan0 target + Vulkan0 draft
 MTP: --spec-type draft-mtp
 speculative.n_max: 2
 speculative.n_min: 0
 speculative.p_min: 0.75
@@ -238,6 +243,30 @@ chat template: Step native tool_response template with protocol-boundary escapin
 Serving backend note: on the tested AMD Ryzen AI Max+ 395 / Strix Halo system, this Step 3.7 Q3 build worked best through the ROCmFPX/Chadrock runner serving on `Vulkan0` for both target and draft. In the command below, ROCmFPX is the required tensor/runtime support; `-dev Vulkan0` and `--spec-draft-device Vulkan0` are the recommended serving backend.
 Example shape:
 ```bash

 Step-3.7-Flash-ROCmFPX-Q3-QualityPlus-00009-of-00009.gguf
 ```
+The Step MTP draft model is not duplicated here. If you enable `draft-mtp`, you
+must also download and pass the separate Q8 draft from
+[`notSnix/Step-3.7-Flash-MTP-Draft-GGUF`](https://huggingface.co/notSnix/Step-3.7-Flash-MTP-Draft-GGUF),
+for example `Step-3.7-Flash-MTP-Q8_0.gguf`. The main Q3 target GGUF does not
+contain the MTP draft layers.
 This repo also includes the tested chat/tool template:
 slots: 1
 backend: Vulkan0 target + Vulkan0 draft
 MTP: --spec-type draft-mtp
+draft model: Step-3.7-Flash-MTP-Q8_0.gguf from notSnix/Step-3.7-Flash-MTP-Draft-GGUF
 speculative.n_max: 2
 speculative.n_min: 0
 speculative.p_min: 0.75
 Serving backend note: on the tested AMD Ryzen AI Max+ 395 / Strix Halo system, this Step 3.7 Q3 build worked best through the ROCmFPX/Chadrock runner serving on `Vulkan0` for both target and draft. In the command below, ROCmFPX is the required tensor/runtime support; `-dev Vulkan0` and `--spec-draft-device Vulkan0` are the recommended serving backend.
+For `models.ini`-style launchers, make sure the draft path is present. Setting
+`spec-type = draft-mtp` without `spec-draft-model` makes the runner try to build
+an MTP draft context from the main target GGUF, which fails because the target
+does not contain MTP draft layers.
+```ini
+model = /mnt/models/jcbtc-Step-3.7-Flash-ROCmFPX-Q3-QualityPlus/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus-00001-of-00009.gguf
+chat-template-file = /mnt/models/jcbtc-Step-3.7-Flash-ROCmFPX-Q3-QualityPlus/step37-native-tool-response-template.jinja
+spec-type = draft-mtp
+spec-draft-model = /mnt/models/notSnix-Step-3.7-Flash-MTP-Draft-GGUF/Step-3.7-Flash-MTP-Q8_0.gguf
+spec-draft-device = Vulkan0
+spec-draft-ngl = all
+spec-draft-type-k = q8_0
+spec-draft-type-v = q8_0
+spec-draft-n-max = 2
+spec-draft-n-min = 0
+spec-draft-p-min = 0.75
+spec-draft-p-split = 0.10
+```
+If you see `context type MTP requested but model doesn't contain MTP layers`,
+the draft model is missing or the path is wrong.
 Example shape:
 ```bash