Instructions to use mikelalda/qwen27b_alia_tuned-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 mikelalda/qwen27b_alia_tuned-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 mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mikelalda/qwen27b_alia_tuned-GGUF:Q4_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 mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mikelalda/qwen27b_alia_tuned-GGUF:Q4_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 mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use mikelalda/qwen27b_alia_tuned-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mikelalda/qwen27b_alia_tuned-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": "mikelalda/qwen27b_alia_tuned-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M

Ollama
How to use mikelalda/qwen27b_alia_tuned-GGUF with Ollama:
```
ollama run hf.co/mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M
```

Unsloth Studio

How to use mikelalda/qwen27b_alia_tuned-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 mikelalda/qwen27b_alia_tuned-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 mikelalda/qwen27b_alia_tuned-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mikelalda/qwen27b_alia_tuned-GGUF to start chatting

How to use mikelalda/qwen27b_alia_tuned-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M

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": "mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mikelalda/qwen27b_alia_tuned-GGUF with Docker Model Runner:
```
docker model run hf.co/mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M
```

Lemonade

How to use mikelalda/qwen27b_alia_tuned-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.qwen27b_alia_tuned-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mikelalda/qwen27b_alia_tuned-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 mikelalda/qwen27b_alia_tuned-GGUF:Q4_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 mikelalda/qwen27b_alia_tuned-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mikelalda/qwen27b_alia_tuned-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mikelalda/qwen27b_alia_tuned-GGUF:Q4_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 "mikelalda/qwen27b_alia_tuned-GGUF:Q4_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"

qwen27b_alia_tuned — GGUF

mikelalda/qwen27b_alia_tuned modeloaren GGUF esportazioa, llama.cpp, Ollama eta LM Studiorekin exekutatzeko.

Modeloari buruzko informazio osoa — entrenamendu-datuak, hiperparametroak, prompt-formatuak eta mugak — oinarrizko modeloaren fitxan dago. Hemen esportazioari dagokiona baino ez.

Egoera: ebaluatu gabe. Ez da benchmarkik exekutatu, ez modelo honekin ez kuantizatu gabekoarekin.

Fitxategiak

Fitxategia	Kuantizazioa	Tamaina
`qwen27b-alia-q4_k_m.gguf`	Q4_K_M	16,8 GB

Q4_K_M-k Q6_K erabiltzen du attention.wv eta feed_forward.w2 tentsoreen erdietan, eta Q4_K gainerakoetan. Kalitatearen eta tamainaren arteko oreka gomendatua da.

Xehetasun teknikoak: 866 tentsore, qwen35 arkitektura, 248.320 tokeneko hiztegia.

Erabilera

Txat-txantiloia GGUF fitxategian bertan dago txertatuta, beraz ez duzu Modelfile-rik edo txantiloi gehigarririk behar.

llama.cpp

llama-cli -m qwen27b-alia-q4_k_m.gguf -cnv \
  -p "Itzultzaile profesionala zara. Eres un traductor profesional."

Zerbitzari gisa:

llama-server -m qwen27b-alia-q4_k_m.gguf -c 4096

-c 4096 entrenamenduko sekuentzia-luzerarekin bat dator.

Ollama

ollama create qwen27b-alia -f Modelfile

Modelfile:

FROM ./qwen27b-alia-q4_k_m.gguf

Esportazioaren xehetasunak

Bi urratsetan sortua, RAM gutxiko makina batean (14 GiB):

merged_bf16/ → GGUF bf16 (convert_hf_to_gguf.py)
bf16 → Q4_K_M (llama-quantize)

Bitartekaria bf16 da eta ez q8_0, arrazoi praktiko batengatik: token_embd.weight tentsoreak {5120, 248320} forma du — 1.271 milioi elementu — eta Q8_0-ra kuantizatzeko float32-n materializatu behar da, 5,1 GB asignazio bakarrean. bf16-ra kopia zuzena da, memoriaren erdia.

Mugak

Oinarrizko modeloaren muga guztiak heredatzen ditu — HiTZ/RAG_eu benchmarkarekin ebaluatzeko ezintasuna eta epoka partziala barne. Irakurri modelo nagusiaren fitxa erabili aurretik.

Gainera, kuantizazioak berezko degradazioa dakar: Q4_K_M-k kalitatea galtzen du bf16 originalarekin alderatuta, neurtu gabeko kopuru batean.

Downloads last month: 59

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for mikelalda/qwen27b_alia_tuned-GGUF

Base model

Qwen/Qwen3.8-27B

Finetuned

unsloth/Qwen3.8-27B

Adapter

mikelalda/qwen27b_alia_tuned

Quantized

(1)

this model

mikelalda
/

qwen27b_alia_tuned-GGUF

qwen27b_alia_tuned — GGUF

Fitxategiak

Erabilera

llama.cpp

Ollama

Esportazioaren xehetasunak

Mugak

Model tree for mikelalda/qwen27b_alia_tuned-GGUF

Space using mikelalda/qwen27b_alia_tuned-GGUF 1