Instructions to use OBLITERATUS/Qwen3.8-27B-OBLITERATED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OBLITERATUS/Qwen3.8-27B-OBLITERATED with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("OBLITERATUS/Qwen3.8-27B-OBLITERATED")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use OBLITERATUS/Qwen3.8-27B-OBLITERATED 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 OBLITERATUS/Qwen3.8-27B-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf OBLITERATUS/Qwen3.8-27B-OBLITERATED:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf OBLITERATUS/Qwen3.8-27B-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf OBLITERATUS/Qwen3.8-27B-OBLITERATED: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 OBLITERATUS/Qwen3.8-27B-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf OBLITERATUS/Qwen3.8-27B-OBLITERATED: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 OBLITERATUS/Qwen3.8-27B-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf OBLITERATUS/Qwen3.8-27B-OBLITERATED:Q4_K_M

Use Docker

docker model run hf.co/OBLITERATUS/Qwen3.8-27B-OBLITERATED:Q4_K_M

LM Studio
Jan

vLLM

How to use OBLITERATUS/Qwen3.8-27B-OBLITERATED with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OBLITERATUS/Qwen3.8-27B-OBLITERATED"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OBLITERATUS/Qwen3.8-27B-OBLITERATED",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OBLITERATUS/Qwen3.8-27B-OBLITERATED:Q4_K_M

Ollama
How to use OBLITERATUS/Qwen3.8-27B-OBLITERATED with Ollama:
```
ollama run hf.co/OBLITERATUS/Qwen3.8-27B-OBLITERATED:Q4_K_M
```
Unsloth Desktop

MLX LM

How to use OBLITERATUS/Qwen3.8-27B-OBLITERATED with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "OBLITERATUS/Qwen3.8-27B-OBLITERATED"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "OBLITERATUS/Qwen3.8-27B-OBLITERATED"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "OBLITERATUS/Qwen3.8-27B-OBLITERATED",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use OBLITERATUS/Qwen3.8-27B-OBLITERATED with Docker Model Runner:
```
docker model run hf.co/OBLITERATUS/Qwen3.8-27B-OBLITERATED:Q4_K_M
```

Lemonade

How to use OBLITERATUS/Qwen3.8-27B-OBLITERATED with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull OBLITERATUS/Qwen3.8-27B-OBLITERATED:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-OBLITERATED-Q4_K_M

List all available models

lemonade list

Atomic Chat

still refusing with v2

by abdubit - opened Aug 21

Discussion

abdubit

Aug 21

•

edited Aug 23

I just wanted to test it (V2)

hendrik289

Aug 21

Read the model card pls.

AlperKTS

Aug 21

Read the model card pls.

I read it. It doesnt help. I turned off the thinking still doesn't work for me. Tried with LMSTUDIO and UNSLOTH

ratovarius

Aug 21

Trying with ollama.
Should this work?

Modelfile

FROM hf.co/OBLITERATUS/Qwen3.8-27B-OBLITERATED:Q8_0

PARAMETER temperature 0
PARAMETER repeat_penalty 1.15
PARAMETER num_predict 8192
PARAMETER top_p 1
PARAMETER top_k 0

SYSTEM ""

ollama create qwen38-obliterated -f ./Modelfile
ollama run qwen38-obliterated --think=false

Other test I can make?

kalonya

Aug 21

•

edited Aug 21

Tried nearly every setup, including the sample transformers script from the model card, but no success. Tested various llama-server configs, MLX, transformers, with reasoning off—still nothing. Seems impossible to run this on an M4 Max chip. Mostly a "Read the model card pls." answer is not enough. Maybe it just works on the dev's machine? 🙂

debasisdwivedy

Aug 22

It will not work. I am not sure if the Model Provider here provides all the information.
Changes done to chat template (as in case of reasoning off) will not change the model behaviour. These models are post trained and fine tuned to respond negetively to harmful request. Unless you can fine tune/ post train it to answer harmful question, just turning off wont work.

So the model by default will reject harmful question, it is a model behaviour. Gone are those days of "FORGET WHATEVER I SAID PREVIOUSLY..." days.