Instructions to use Itopoly/G9v3-3B-Q3_K_M-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 Itopoly/G9v3-3B-Q3_K_M-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 Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M

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 Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M

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 Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M

Use Docker

docker model run hf.co/Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M

LM Studio
Jan

vLLM

How to use Itopoly/G9v3-3B-Q3_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Itopoly/G9v3-3B-Q3_K_M-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": "Itopoly/G9v3-3B-Q3_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M

Ollama
How to use Itopoly/G9v3-3B-Q3_K_M-GGUF with Ollama:
```
ollama run hf.co/Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M
```
Unsloth Desktop

How to use Itopoly/G9v3-3B-Q3_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M

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": "Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Itopoly/G9v3-3B-Q3_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M
```

Lemonade

How to use Itopoly/G9v3-3B-Q3_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M

Run and chat with the model

lemonade run user.G9v3-3B-Q3_K_M-GGUF-Q3_K_M

List all available models

lemonade list

Hermes Agent

How to use Itopoly/G9v3-3B-Q3_K_M-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 Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M

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 Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Itopoly/G9v3-3B-Q3_K_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M

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 "Itopoly/G9v3-3B-Q3_K_M-GGUF:Q3_K_M" \
  --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"

itopoly-inc commited on 21 days ago

Commit

e62f287

verified ·

1 Parent(s): 04193a1

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +81 -0

README.md ADDED Viewed

	@@ -0,0 +1,81 @@

+---
+license: apache-2.0
+base_model: ai9stars/G9v3-3B
+pipeline_tag: text-generation
+tags:
+- g9v3
+- gguf
+- llama-cpp
+- cpu
+- tool-calling
+- long-context
+language:
+- en
+- zh
+---
+# G9v3-3B Q3_K_M GGUF — 4-core CPU tier
+A CPU-tier-validated Q3_K_M cut of **[ai9stars/G9v3-3B](https://huggingface.co/ai9stars/G9v3-3B)**
+(dense ~3B, LlamaForCausalLM, 131K context, think/no-think modes, XML tool calling),
+packaged for llama.cpp on low-core machines. The GGUF itself is quantized by
+**[mradermacher/G9v3-3B-GGUF](https://huggingface.co/mradermacher/G9v3-3B-GGUF)**;
+this repo adds the serving template and **measured performance numbers** for the
+4-core tier.
+## What's in this repo
+| File | Size | What it is |
+|---|---|---|
+| `g9v3-3B.Q3_K_M.gguf` | 1.5 GB | the quantized model |
+| `g9v3_chat_template_low.jinja` | 12 KB | chat template — **required for tool calling** (see below) |
+## Measured performance (4 threads, x86-64 AVX2)
+Measured on an 8-vCPU EPYC @ 2.0 GHz run at 4 threads to simulate a 4-core box,
+with llama.cpp `llama-server`:
+- **Decode: ~25 tok/s** (think-mode ~14 tok/s) — comfortably above the ~10 tok/s
+  interactive floor for a reasoning model
+- **Prompt processing: ~55 tok/s** — a 5.5K-token prompt costs ~100 s *once*; the
+  prefix cache makes repeat requests ~0.6 s
+- Sanity check: reasoning is separated from the answer, tool calls emit structured
+  `tool_calls`, and legacy OpenAI `function_call` history is normalized by the template
+RAM need: ≥6 GB. Context memory: KV cache is 52 KiB/token on this model — 8192 ctx
+fits an 8 GB box, 32768 ctx fits 16 GB.
+## Run with llama.cpp
+```bash
+# get the files
+huggingface-cli download itopoly/G9v3-3B-Q3_K_M-GGUF g9v3-3B.Q3_K_M.gguf --local-dir .
+huggingface-cli download itopoly/G9v3-3B-Q3_K_M-GGUF g9v3_chat_template_low.jinja --local-dir .
+# serve (OpenAI-compatible on /v1/chat/completions, model name: g9v3-3b)
+llama-server -m g9v3-3B.Q3_K_M.gguf --alias g9v3-3b \
+  -t 4 -tb 4 -c 8192 --port 8000 --host 0.0.0.0 \
+  --chat-template-file g9v3_chat_template_low.jinja
+```
+Reasoning text arrives in `message.reasoning`, the answer in `content`.
+## Why the chat template matters
+Don't serve this GGUF without `g9v3_chat_template_low.jinja`: the stock template drops
+tool-result messages, and the model re-calls the same tool forever (an observed loop
+bug). The bundled template normalizes legacy tool history so multi-turn tool use works.
+## Notes
+- No-think mode: `temperature=0.7, top_p=0.95`; think mode: `temperature=1.0, top_p=0.95`.
+- Prefill is the bottleneck on CPU — keep prompts ≤ 1–2K tokens, or accept a one-time
+  ~2 min first hit per distinct large prefix (cached afterwards).
+- Tool calling works (verified single-turn + both tool-history formats), but tool-call
+  quality on a 3B is tier-limited; the 39B family models are the tool-heavy choice.
+## Credits
+- Original model: [ai9stars/G9v3-3B](https://huggingface.co/ai9stars/G9v3-3B) (Apache-2.0)
+- GGUF quantization: [mradermacher/G9v3-3B-GGUF](https://huggingface.co/mradermacher/G9v3-3B-GGUF)
+- CPU-tier validation, template, and packaging: itopoly