Instructions to use Harsha001/flint-ROCmFPX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Harsha001/flint-ROCmFPX 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 Harsha001/flint-ROCmFPX:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf Harsha001/flint-ROCmFPX:Q4_0_ROCMFP

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Harsha001/flint-ROCmFPX:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf Harsha001/flint-ROCmFPX:Q4_0_ROCMFP

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 Harsha001/flint-ROCmFPX:Q4_0_ROCMFP
# Run inference directly in the terminal:
./llama-cli -hf Harsha001/flint-ROCmFPX:Q4_0_ROCMFP

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 Harsha001/flint-ROCmFPX:Q4_0_ROCMFP
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Harsha001/flint-ROCmFPX:Q4_0_ROCMFP

Use Docker

docker model run hf.co/Harsha001/flint-ROCmFPX:Q4_0_ROCMFP

LM Studio
Jan

vLLM

How to use Harsha001/flint-ROCmFPX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Harsha001/flint-ROCmFPX"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Harsha001/flint-ROCmFPX",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Harsha001/flint-ROCmFPX:Q4_0_ROCMFP

Ollama
How to use Harsha001/flint-ROCmFPX with Ollama:
```
ollama run hf.co/Harsha001/flint-ROCmFPX:Q4_0_ROCMFP
```
Unsloth Desktop

How to use Harsha001/flint-ROCmFPX with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Harsha001/flint-ROCmFPX:Q4_0_ROCMFP

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": "Harsha001/flint-ROCmFPX:Q4_0_ROCMFP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Harsha001/flint-ROCmFPX with Docker Model Runner:
```
docker model run hf.co/Harsha001/flint-ROCmFPX:Q4_0_ROCMFP
```

Lemonade

How to use Harsha001/flint-ROCmFPX with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Harsha001/flint-ROCmFPX:Q4_0_ROCMFP

Run and chat with the model

lemonade run user.flint-ROCmFPX-Q4_0_ROCMFP

List all available models

lemonade list

Hermes Agent

How to use Harsha001/flint-ROCmFPX with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Harsha001/flint-ROCmFPX:Q4_0_ROCMFP

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 Harsha001/flint-ROCmFPX:Q4_0_ROCMFP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Harsha001/flint-ROCmFPX with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Harsha001/flint-ROCmFPX:Q4_0_ROCMFP

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 "Harsha001/flint-ROCmFPX:Q4_0_ROCMFP" \
  --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"

Harsha001 commited on 1 day ago

Commit

9a4ca35

verified ·

1 Parent(s): 39ae095

Rename the 6-bit file to Q6_K_ROCMFPX so the Hub lists it as 6-bit

Browse files

Files changed (3) hide show

.gitattributes +1 -0
README.md +3 -1
flint-Q6_0_ROCMFPX.gguf → flint-Q6_K_ROCMFPX.gguf +0 -0

.gitattributes CHANGED Viewed

@@ -39,3 +39,4 @@ flint-Q4_0_ROCMFP4_STRIX.gguf filter=lfs diff=lfs merge=lfs -text
 flint-Q4_0_ROCMFP4_FAST.gguf filter=lfs diff=lfs merge=lfs -text
 flint-Q4_0_ROCMFP4_Q8ATTN.gguf filter=lfs diff=lfs merge=lfs -text
 flint-Q4_0_ROCMFP4_FAST_Q8ATTN.gguf filter=lfs diff=lfs merge=lfs -text

 flint-Q4_0_ROCMFP4_FAST.gguf filter=lfs diff=lfs merge=lfs -text
 flint-Q4_0_ROCMFP4_Q8ATTN.gguf filter=lfs diff=lfs merge=lfs -text
 flint-Q4_0_ROCMFP4_FAST_Q8ATTN.gguf filter=lfs diff=lfs merge=lfs -text
+flint-Q6_K_ROCMFPX.gguf filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -36,10 +36,12 @@ often the quant picks the same next token as BF16.
 | File | Size | PPL | KLD | Same top | |
 |---|---:|---:|---:|---:|---|
 | `flint-Q8_0_ROCMFPX.gguf` | 41.1 GB | 19.1675 | 0.0747 | 91.02% | 8-bit, closest to BF16 |
-| `flint-Q6_0_ROCMFPX.gguf` | 32.9 GB | 19.7449 | 0.0917 | 89.63% | 6-bit, almost as close as 8-bit |
 | `flint-Q4_0_ROCMFP4_Q8ATTN.gguf` | 23.3 GB | 18.891 | 0.1777 | 84.96% | **Recommended 4-bit** (see below) |
 | `flint-Q4_0_ROCMFP4_FAST_Q8ATTN.gguf` | 22.1 GB | 18.722 | 0.2071 | 84.23% | speed-first 4-bit: experts with one scale per block |
 For comparison, a stock llama.cpp `Q4_K_M` of the same model (23 GB), scored the same way, measured PPL 19.92,
 KLD 0.2449, same top 82.94%. Both 4-bit files here are closer to BF16 and smaller.

 | File | Size | PPL | KLD | Same top | |
 |---|---:|---:|---:|---:|---|
 | `flint-Q8_0_ROCMFPX.gguf` | 41.1 GB | 19.1675 | 0.0747 | 91.02% | 8-bit, closest to BF16 |
+| `flint-Q6_K_ROCMFPX.gguf` | 32.9 GB | 19.7449 | 0.0917 | 89.63% | 6-bit, almost as close as 8-bit |
 | `flint-Q4_0_ROCMFP4_Q8ATTN.gguf` | 23.3 GB | 18.891 | 0.1777 | 84.96% | **Recommended 4-bit** (see below) |
 | `flint-Q4_0_ROCMFP4_FAST_Q8ATTN.gguf` | 22.1 GB | 18.722 | 0.2071 | 84.23% | speed-first 4-bit: experts with one scale per block |
+The 6-bit file is named `flint-Q6_K_ROCMFPX.gguf` so that Hugging Face lists it as a 6-bit quant. Its weights are the ROCmFPX `Q6_0_ROCMFPX` type, not a stock llama.cpp `Q6_K`, and it needs the same fork as the other files.
 For comparison, a stock llama.cpp `Q4_K_M` of the same model (23 GB), scored the same way, measured PPL 19.92,
 KLD 0.2449, same top 82.94%. Both 4-bit files here are closer to BF16 and smaller.

flint-Q6_0_ROCMFPX.gguf → flint-Q6_K_ROCMFPX.gguf RENAMED Viewed

File without changes