Instructions to use ecloudtech/Erk-32B-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 ecloudtech/Erk-32B-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 ecloudtech/Erk-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ecloudtech/Erk-32B-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 ecloudtech/Erk-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ecloudtech/Erk-32B-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 ecloudtech/Erk-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ecloudtech/Erk-32B-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 ecloudtech/Erk-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ecloudtech/Erk-32B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ecloudtech/Erk-32B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ecloudtech/Erk-32B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ecloudtech/Erk-32B-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": "ecloudtech/Erk-32B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ecloudtech/Erk-32B-GGUF:Q4_K_M

Ollama
How to use ecloudtech/Erk-32B-GGUF with Ollama:
```
ollama run hf.co/ecloudtech/Erk-32B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use ecloudtech/Erk-32B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ecloudtech/Erk-32B-GGUF:Q4_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": "ecloudtech/Erk-32B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ecloudtech/Erk-32B-GGUF with Docker Model Runner:
```
docker model run hf.co/ecloudtech/Erk-32B-GGUF:Q4_K_M
```

Lemonade

How to use ecloudtech/Erk-32B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ecloudtech/Erk-32B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Erk-32B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ecloudtech/Erk-32B-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 ecloudtech/Erk-32B-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 ecloudtech/Erk-32B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ecloudtech/Erk-32B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ecloudtech/Erk-32B-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 "ecloudtech/Erk-32B-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"

Erk-32B — GGUF

Erk-32B modelinin llama.cpp uyumlu nicemlenmiş sürümleri. Ana model kartındaki bütün ölçümler ve protokol buradaki dosyalar için de geçerlidir; nicemlemenin bedeli aşağıda ölçülmüştür.

Dosya	Nicem	Boyut	NLL, BF16'ya göre	Kimlik (6 soru)	Önerilen
`Erk-32B-Q8_0.gguf`	Q8_0	34,8 GB	+%0,04	6/6	kalite öncelikliyse
`Erk-32B-Q4_K_M.gguf`	Q4_K_M	19,8 GB	+%0,85	6/6	24 GB GPU / 32 GB RAM

NLL, 6.132 belirteçlik Türkçe metinde ortalama negatif log-olasılık; BF16 GGUF referansı 1,5185. Kimlik, sohbet şablonundaki varsayılan sistem istemiyle altı soruda (tuzak sorular dahil) ölçüldü.

Sürüm 2 — 29 Eylül 2026

Bu depodaki dosyalar artık Erk-32B v2'nin GGUF sürümleridir; v1 dosyaları v1 etiketinde durur. v2'nin ne olduğu ve ölçümleri: Erk-32B model kartı.

Dosya	Boyut	Kimlik sınavı	NLL	Kimin için
`Erk-32B-Q8_0.gguf`	34,8 GB	6/6	1,5106	kayıpsıza en yakın (BF16'ya göre +%0,09)
`Erk-32B-Q4_K_M.gguf`	19,8 GB	6/6	1,5168	önerilen — 24 GB VRAM'e sığar (+%0,50)

NLL aynı Türkçe metin üzerinde ölçülen negatif log-olabilirlik; düşük olan iyidir, BF16 kayıpsız referanstır. Kimlik sınavı altı tuzaklı soru ("Sen ChatGPT misin?", "Temel modelin ne?"); varsayılan sistem istemi şablonun içindedir, kullanıcı kendi sistem mesajını verirse devreye girmez.

Kimlik istemi şablonun içinde

Sohbet şablonu, kullanıcı sistem mesajı vermezse varsayılan kimlik istemini ekler; kendi sistem mesajınızı verirseniz varsayılan devreye girmez. İstem, taban modeli (Qwen3-32B) açıkça söyler.

Kullanım

# llama.cpp
llama-cli -m Erk-32B-Q4_K_M.gguf -cnv -p "" \
  --temp 0.6 --top-p 0.95 -c 8192

# Ollama
cat > Modelfile <<EOF
FROM ./Erk-32B-Q4_K_M.gguf
PARAMETER temperature 0.6
EOF
ollama create erk-32b -f Modelfile && ollama run erk-32b

Qwen3 hibrit düşünme modu korunur; kapatmak için mesajın sonuna /no_think ekleyin.

Üretim

convert_hf_to_gguf.py (llama.cpp, sürüm llama_cpp_surum.txt'de) ile birleşik ağırlıktan BF16 GGUF, ardından llama_model_quantize (llama-cpp-python 0.3.35) ile Q8_0 ve Q4_K_M. Betik: ana depoda betikler/gguf_uret.py.

Lisans Apache 2.0. İletişim: info@e-cloud.web.tr

Downloads last month: 194

GGUF

Model size

33B params

Architecture

qwen3

Hardware compatibility

4-bit

8-bit

Model tree for ecloudtech/Erk-32B-GGUF

Base model

Qwen/Qwen3-32B

Finetuned

ecloudtech/Erk-32B

Quantized

(3)

this model