Instructions to use Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ",
	filename="Qwen3.6-27B-PRISM-PRO-DQ.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ
# Run inference directly in the terminal:
llama-cli -hf Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ
# Run inference directly in the terminal:
llama-cli -hf Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ

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 Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ
# Run inference directly in the terminal:
./llama-cli -hf Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ

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 Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ

Use Docker

docker model run hf.co/Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ

LM Studio
Jan

vLLM

How to use Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ

Ollama
How to use Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ with Ollama:
```
ollama run hf.co/Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ
```

Unsloth Studio new

How to use Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ 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 Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ 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 Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ to start chatting

Pi new

How to use Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ

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": "Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ

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 Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ

Run Hermes

hermes

Docker Model Runner
How to use Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ with Docker Model Runner:
```
docker model run hf.co/Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ
```

Lemonade

How to use Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ

Run and chat with the model

lemonade run user.Qwen3.6-27B-PRISM-PRO-DQ-{{QUANT_TAG}}

List all available models

lemonade list

Qwen3.6-27B-PRISM-PRO-DQ / README.md

Ex0bit

Update README.md

d3f5d79 verified 4 days ago

preview code

raw

history blame contribute delete

2.41 kB

metadata

license: apache-2.0
base_model:
  - Qwen/Qwen3.6-27B
library_name: gguf
pipeline_tag: text-generation
tags:
  - gguf
  - quantized
  - dynamic-quant
  - qwen3
  - llama.cpp
  - speculative-decoding

Qwen3.6-27B-PRISM-PRO — DQ GGUF

llama.cpp-native GGUF quantization of Qwen3.6-27B-PRISM-PRO using the PRISM project's dynamic-quant (DQ) recipe. ~13.7 GB (vs 55 GB BF16).

PRISM-PRO of Qwen/Qwen3.6-27B (bias/propoganda removal) This GGUF preserves the model's native MTP draft head + full vision tower, and pairs with the separately-published EAGLE-3 drafter for lossless faster decode.

Performance

llama.cpp on a single NVIDIA Blackwell GPU, single-stream greedy decode:

config	tok/s	speedup
no-spec baseline	80	1.00×
native MTP (built-in draft head)	121	1.51×
EAGLE-3 chain (with our drafter)	111	1.39×

Speculative decoding is lossless (output token-identical to non-spec greedy, modulo batched-verify floating-point non-associativity intrinsic to all spec decoding). For a faster SGLang deployment (~183 tok/s, ~1.97× over no-spec) using the BF16 target + EAGLE-3, see the drafter repo.

Quick start (llama.cpp)

# 1. no-spec baseline
./llama-server --model Qwen3.6-27B-PRISM-PRO-DQ.gguf

# 2. native MTP speculative decoding (the model's own draft head -- fastest in llama.cpp)
./llama-server --model Qwen3.6-27B-PRISM-PRO-DQ.gguf \
    --spec-type draft-mtp --spec-draft-n-max 1 --spec-draft-n-min 1

# 3. EAGLE-3 chain (needs the WIP PR #18039 patches + the RS-rollback fix --
#    a one-shot llama.cpp patch script is documented alongside the drafter:
#    https://huggingface.co/Ex0bit/Qwen3.6-27B-PRISM-EAGLE3)
./llama-server --model Qwen3.6-27B-PRISM-PRO-DQ.gguf \
    --spec-type draft-eagle3 --model-draft <eagle3-drafter.gguf> \
    --spec-draft-n-max 2

Provenance

Base: Qwen/Qwen3.6-27B (hybrid: 48 GatedDeltaNet linear-attention layers
- 16 full-attention layers; hidden 5120; vocab 248 320; native MTP head).
PRISM Dynamic Quantization: PRISM DQ recipe (llama.cpp GGUF dynamic quant) — preserves the MTP draft head (15 tensors) and the full vision tower (333 tensors).

License

Apache-2.0. Derived from Qwen/Qwen3.6-27B (Apache-2.0).