Instructions to use eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp 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("eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp")

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)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp"

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 eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp"

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 "eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp

MLX oQ4e quantization of OBLITERATUS/Qwen3.8-27B-OBLITERATED (V3 – Deep Liberation).

Quantized with oMLX v0.6.3rc3.

The model includes the MTP (Multi-Token Prediction) weights for speculative decoding with compatible runtimes.

The original vision components have been removed to reduce memory usage. This release is therefore text-only.

It also includes the Qwen Sharp Chat Template, optimized for more concise and token-efficient Qwen 3.8 responses.

Quantization details

Base model: OBLITERATUS/Qwen3.8-27B-OBLITERATED (V3)
Original base: Qwen/Qwen3.8-27B
Quantization: oQ4e
Quantizer: oMLX 0.6.3rc3
Format: MLX Safetensors
MTP: Included
Vision: Removed
Chat template: Qwen Sharp

Downloads last month: 310

Safetensors

Model size

27B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp

Base model

Qwen/Qwen3.8-27B

Quantized

OBLITERATUS/Qwen3.8-27B-OBLITERATED

Quantized

(14)

this model