Instructions to use SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf",
	filename="Ameena_Qwen3-8B_e3.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_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 SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf
# Run inference directly in the terminal:
llama cli -hf SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf
# Run inference directly in the terminal:
llama cli -hf SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf

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 SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf
# Run inference directly in the terminal:
./llama-cli -hf SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf

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 SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf

Use Docker

docker model run hf.co/SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf

LM Studio
Jan
Ollama
How to use SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf with Ollama:
```
ollama run hf.co/SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf
```

Unsloth Studio

How to use SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_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 SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_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 SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf to start chatting

How to use SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf

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": "SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_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 SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf

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 SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf

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 "SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf" \
  --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 SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf with Docker Model Runner:
```
docker model run hf.co/SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf
```

Lemonade

How to use SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SaidzodaEng/Ameena_Qwen3-8B_e3_Quantised_gguf

Run and chat with the model

lemonade run user.Ameena_Qwen3-8B_e3_Quantised_gguf-{{QUANT_TAG}}

List all available models

lemonade list

Ameena_Qwen3-8B_e3_Quantised_gguf / README.md

Tohirju

Upload README.md with huggingface_hub

a170b87 verified 12 months ago

preview code

Raw

History Blame Contribute Delete

2.05 kB

metadata

library_name: gguf
base_model: Qwen/Qwen3-8B
quantized_by: Tohirju
model_name: Ameena_Qwen3-8B_e3_Quantised_gguf
model_author: Tohirju
model_type: qwen3
quantization_method: Q4_K_M
tags:
  - quantized
  - gguf
  - qwen3
  - 8b
  - q4_k_m
license: apache-2.0

Ameena Qwen3-8B e3 Quantized GGUF

This is a quantized version of a fine-tuned Qwen3-8B model, optimized for efficient inference.

Model Details

Base Model: Qwen/Qwen3-8B
Quantization: Q4_K_M (4-bit with K-quant mixed precision)
Original Size: ~15.26 GB
Quantized Size: ~4.68 GB
Compression Ratio: 3.3x
Format: GGUF (GPT-Generated Unified Format)

Usage

With llama-cpp-python

from llama_cpp import Llama

# Load the model
llm = Llama(
    model_path="Ameena_Qwen3-8B_e3.gguf",
    n_gpu_layers=-1,  # Use GPU acceleration
    n_ctx=4096,       # Context window
    verbose=False
)

# Generate text
response = llm(
    "Your prompt here",
    max_tokens=512,
    temperature=0.7,
    top_p=0.9
)

With Hugging Face Transformers + llama.cpp

# Download the model
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(
    repo_id="Tohirju/Ameena_Qwen3-8B_e3_Quantised_gguf",
    filename="Ameena_Qwen3-8B_e3.gguf"
)

Quantization Details

Method: Q4_K_M - Mixed precision 4-bit quantization
Quality: Excellent balance between model size and performance
Speed: Optimized for fast inference on both CPU and GPU
Memory: Significantly reduced VRAM requirements

Performance

Inference Speed: ~3.3x faster loading due to smaller file size
Memory Usage: ~69% reduction in memory requirements
Quality: Minimal quality loss compared to FP16 version

Hardware Requirements

CPU: Any modern CPU (optimized for x86_64)
GPU: CUDA-compatible GPU recommended (RTX 3060+ or better)
RAM: 8GB minimum, 16GB recommended
Storage: ~5GB for the model file

License

This model follows the Apache 2.0 license of the base Qwen3-8B model.