Instructions to use analogalok/Qwen3.8-27B-DFlash2-Q2_K-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 analogalok/Qwen3.8-27B-DFlash2-Q2_K-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 analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K

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 analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K

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 analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K

Use Docker

docker model run hf.co/analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "analogalok/Qwen3.8-27B-DFlash2-Q2_K-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": "analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K

Ollama
How to use analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF with Ollama:
```
ollama run hf.co/analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K
```

Unsloth Studio

How to use analogalok/Qwen3.8-27B-DFlash2-Q2_K-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 analogalok/Qwen3.8-27B-DFlash2-Q2_K-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 analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF to start chatting

How to use analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K

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": "analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF with Docker Model Runner:
```
docker model run hf.co/analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K
```

Lemonade

How to use analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K

Run and chat with the model

lemonade run user.Qwen3.8-27B-DFlash2-Q2_K-GGUF-Q2_K

List all available models

lemonade list

Hermes Agent

How to use analogalok/Qwen3.8-27B-DFlash2-Q2_K-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 analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K

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 analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K

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 "analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF:Q2_K" \
  --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"

Qwen3.8-27B-DFlash2-Q2_K (2-Bit Zero-Loss Speculative Drafter)

This repository provides the Q2_K (2-bit) quantization of z-lab/Qwen3.8-27B-DFlash2 (~700 MB on disk).

It is engineered specifically for 24GB consumer GPUs (NVIDIA GeForce RTX 4090 / RTX 3090) to run speculative decoding alongside Qwen3.8-27B dense models without spilling into system RAM.

🚀 Benchmark Discovery: Zero Quality Loss at 2-Bit

By quantizing the DFlash 2 block-diffusion drafter down from the official Q4_K_M (~~1.1 GB) to Q2_K (~~700 MB), we save ~400–450 MB of VRAM with zero degradation in speculative draft accuracy.

Strict A/B Performance on Single RTX 4090 (24GB VRAM):

Evaluated on Qwen3.8-27B-UD-Q4_K_XL using llama-server (PR #27342) with --spec-draft-n-max 3 across a 28k prompt baseline.

Drafter Quant	File Size	Mean Accepted Length	Acceptance Rate	Decode Speed	Max Usable Context (24GB VRAM)
Official Q4_K_M	~1.10 GB	2.80 / 3.0 tokens	60.00%	75.89 t/s	150,000 tokens (Q4 KV)
Custom Q2_K (This Repo)	~700 MB	2.81 / 3.0 tokens	60.22%	75.93 t/s	170,000 tokens (+20k)

Key Takeaways:

Identical Acceptance Rate: The target 27B model accepts 2.81 out of 3.0 drafted tokens on average $(93.7% \text{ theoretical efficiency})$, matching the 4-bit drafter identically.
Context Expansion: The ~400 MB saved VRAM directly unlocks:
- 170,000 Context on Q4_0 KV (~76 t/s @ 23.89 GB)
- 100,000 Context on high-precision Q8_0 KV (~75 t/s @ 23.88 GB)

⚙️ Why Q2_K is the True Physical Floor for DFlash 2

DFlash 2 is a cross-layer block-diffusion drafter that extracts hidden states from layers [6, 20, 34, 48, 62] of the base model. Because it is not a standalone causal LM, standalone llama-imatrix calibration fails (dflash requires ctx_other to be set).

This means importance-matrix quants (IQ1_S, IQ2_XXS) cannot be computed, making Q2_K the absolute lowest non-degrading quantization floor for DFlash 2.

🛠️ Quickstart with `llama.cpp`

Requires llama.cpp built from PR #27342.

1. Build `llama.cpp`:

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
git fetch origin pull/27342/head:pr-27342
git switch pr-27342

# Build with CUDA
cmake -B build -DGGML_CUDA=ON && cmake --build build -j

Downloads last month: 497

GGUF

Model size

2B params

Architecture

dflash

Hardware compatibility

2-bit

Model tree for analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF

Base model

Qwen/Qwen3.8-27B

Finetuned

z-lab/Qwen3.8-27B-DFlash2

Quantized

(2)

this model

Qwen3.8-27B-DFlash2-Q2_K (2-Bit Zero-Loss Speculative Drafter)

🚀 Benchmark Discovery: Zero Quality Loss at 2-Bit

Strict A/B Performance on Single RTX 4090 (24GB VRAM):

Key Takeaways:

⚙️ Why Q2_K is the True Physical Floor for DFlash 2

🛠️ Quickstart with llama.cpp

1. Build llama.cpp:

Model tree for analogalok/Qwen3.8-27B-DFlash2-Q2_K-GGUF

🛠️ Quickstart with `llama.cpp`

1. Build `llama.cpp`: