Instructions to use Anbeeld/Qwen3.6-27B-DFlash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Anbeeld/Qwen3.6-27B-DFlash-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("feature-extraction", model="Anbeeld/Qwen3.6-27B-DFlash-GGUF", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Anbeeld/Qwen3.6-27B-DFlash-GGUF", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Anbeeld/Qwen3.6-27B-DFlash-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 Anbeeld/Qwen3.6-27B-DFlash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Anbeeld/Qwen3.6-27B-DFlash-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 Anbeeld/Qwen3.6-27B-DFlash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Anbeeld/Qwen3.6-27B-DFlash-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 Anbeeld/Qwen3.6-27B-DFlash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Anbeeld/Qwen3.6-27B-DFlash-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 Anbeeld/Qwen3.6-27B-DFlash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Anbeeld/Qwen3.6-27B-DFlash-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Anbeeld/Qwen3.6-27B-DFlash-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Anbeeld/Qwen3.6-27B-DFlash-GGUF with Ollama:
```
ollama run hf.co/Anbeeld/Qwen3.6-27B-DFlash-GGUF:Q4_K_M
```

Unsloth Studio

How to use Anbeeld/Qwen3.6-27B-DFlash-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 Anbeeld/Qwen3.6-27B-DFlash-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 Anbeeld/Qwen3.6-27B-DFlash-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Anbeeld/Qwen3.6-27B-DFlash-GGUF to start chatting

How to use Anbeeld/Qwen3.6-27B-DFlash-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Anbeeld/Qwen3.6-27B-DFlash-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": "Anbeeld/Qwen3.6-27B-DFlash-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Anbeeld/Qwen3.6-27B-DFlash-GGUF with Docker Model Runner:
```
docker model run hf.co/Anbeeld/Qwen3.6-27B-DFlash-GGUF:Q4_K_M
```

Lemonade

How to use Anbeeld/Qwen3.6-27B-DFlash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Anbeeld/Qwen3.6-27B-DFlash-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-27B-DFlash-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Anbeeld/Qwen3.6-27B-DFlash-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 Anbeeld/Qwen3.6-27B-DFlash-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 Anbeeld/Qwen3.6-27B-DFlash-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Anbeeld/Qwen3.6-27B-DFlash-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Anbeeld/Qwen3.6-27B-DFlash-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 "Anbeeld/Qwen3.6-27B-DFlash-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"

Anbeeld commited on Jul 15

Commit

8fc4564

verified ·

1 Parent(s): 919826d

Publish DFlash middle-class quantization ladder

Browse files

Files changed (9) hide show

.gitattributes +2 -0
Qwen3.6-27B-DFlash-Q2_K.gguf +3 -0
Qwen3.6-27B-DFlash-Q3_K_M.gguf +3 -0
Qwen3.6-27B-DFlash-Q4_K_M.gguf +2 -2
Qwen3.6-27B-DFlash-Q5_K_M.gguf +2 -2
Qwen3.6-27B-DFlash-Q6_K.gguf +2 -2
Qwen3.6-27B-DFlash-Q8_0.gguf +2 -2
Qwen3.6-27B-DFlash-bf16.gguf +2 -2
README.md +2 -35

.gitattributes CHANGED Viewed

@@ -39,3 +39,5 @@ Qwen3.6-27B-DFlash-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen3.6-27B-DFlash-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen3.6-27B-DFlash-bf16.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen3.6-27B-DFlash-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

 Qwen3.6-27B-DFlash-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen3.6-27B-DFlash-bf16.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen3.6-27B-DFlash-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.6-27B-DFlash-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.6-27B-DFlash-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text

Qwen3.6-27B-DFlash-Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ea9413d506b984251f1124f6a0e320db10998c5f569a24f20bc05930ba3c5baf
+size 640956480

Qwen3.6-27B-DFlash-Q3_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:093dd7621298e7c01f8c7d55bd346bb27a655ff9a5290e5436afe003d3f37c3a
+size 832526400

Qwen3.6-27B-DFlash-Q4_K_M.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af2d6a6fa0fcd1953214143720b8e7d653bc09b3490ef45c5f668badb7a19c0d
-size 1033066880

 version https://git-lfs.github.com/spec/v1
+oid sha256:49508c9d29995e418cf29930e0b7d309c6f60e22e9848573a3b321fd475af88a
+size 1033066560

Qwen3.6-27B-DFlash-Q5_K_M.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec705a77b55b87245fa7639487c5f292127275a632646984b22e68452ebfe8cf
-size 1225742720

 version https://git-lfs.github.com/spec/v1
+oid sha256:cb3cc7f3a2dc0d89df85991ad7745e71c16ad0ec9dcbd5b7c8dcbc7667c4db4f
+size 1225742400

Qwen3.6-27B-DFlash-Q6_K.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20b5ab92bd6a3255c4b2ec892b5a2a9c7026d28fb758e6f627153614d940876
-size 1430460800

 version https://git-lfs.github.com/spec/v1
+oid sha256:d5f70b0476fe92b58c8db22c2fbf9de807ebe0175d7b922a195001ac9848b21c
+size 1430460480

Qwen3.6-27B-DFlash-Q8_0.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:730248220d2e495439171b212084e8309ceae3091c55e2c82e3e742283aaa7d9
-size 1849481600

 version https://git-lfs.github.com/spec/v1
+oid sha256:d1f5415290b37552ff740518f8ae4e8abf9b68ec62b2b00f301e34dc81de0da8
+size 1849481280

Qwen3.6-27B-DFlash-bf16.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:818893375550ccc649ad7cafd9d8fd50a750e7ddf82adff2094b502da4225482
-size 3471497600

 version https://git-lfs.github.com/spec/v1
+oid sha256:84319eb0e83cbe163ca1a0f29823cabc136bdcde0ffaf5ccdb77b42cb1d6c374
+size 3471497280

README.md CHANGED Viewed

@@ -1,36 +1,3 @@
----
-base_model: z-lab/Qwen3.6-27B-DFlash
----
-DFlash draft model for [Qwen 3.6 27B](https://huggingface.co/Qwen/Qwen3.6-27B), made by [z-lab](https://huggingface.co/z-lab/Qwen3.6-27B-DFlash).
-Tested with [BeeLlama.cpp v0.2.0](https://github.com/Anbeeld/beellama.cpp) — a llama.cpp fork with advanced DFlash support that enables using these draft models to their full potential.
-* Target model: [Qwen 3.6 27B Q5_K_S](https://huggingface.co/unsloth/Qwen3.6-27B-GGUF)
-* Setup: Windows 11, AMD Ryzen 7 5700X3D, 32 GB DDR4 RAM, RTX 3090 24 GB
-* Config: same as in [quick start docs](https://github.com/Anbeeld/beellama.cpp/blob/main/docs/quickstart-qwen36-dflash.md), but with reasoning and adaptive DM disabled
-* Baseline is llama.cpp [b9275](https://github.com/ggml-org/llama.cpp/releases/tag/b9275) CUDA 13.1 Windows prebuilt: 36.8 tok/s median
-<details>
-<summary>Prompt: Doubly-linked list (output: ~4K tok)</summary>
-Write a complete Python 3 module implementing a doubly-linked list with the following methods: append, prepend, insert_at, remove_at, find, reverse, to_list, length, is_empty, iter. Include comprehensive docstrings, type hints, and pytest unit tests for every method. Return only the code, no commentary.
-</details>
-| DFlash quant | Size | Median | Best | Speedup | Acceptance |
-| --- | ---: | ---: | ---: | ---: | ---: |
-| IQ4_XS | 891 MB | 148.0 tok/s | 160.5 tok/s | 4.02x | 47.6% / 87.7% |
-| Q4_K_M | 985 MB | 145.6 tok/s | 152.6 tok/s | 3.96x | 47.0% / 87.6% |
-| Q5_K_M | 1.17 GB | 144.9 tok/s | 157.2 tok/s | 3.94x | 46.8% / 87.6% |
-| Q6_K | 1.36 GB | 139.2 tok/s | 152.5 tok/s | 3.79x | 45.4% / 87.2% |
-| Q8_0 | 1.76 GB | 142.8 tok/s | 155.5 tok/s | 3.88x | 46.9% / 87.6% |
-| bf16 | 3.31 GB | 132.5 tok/s | 145.0 tok/s | 3.60x | 44.2% / 86.9% |
-*Acceptance: accepted to proposed draft tokens / accepted draft tokens to final generated tokens*
-Between IQ4_XS, Q4_K_M and Q5_K_M the difference is smaller than noise from variance between passes, so using any of them should be fine. IQ4_XS takes up the least VRAM, but Q5_K_M might result in slightly higher acceptance in the long run.
-Higher quants don't guarantee better performance: the model's job is to predict just a few tokens at the time, so loss of precision doesn't affect it as much. Meanwhile, larger size leads to slower drafting, reducing resulting tok/s, and also more VRAM consumption.
-Keep in mind that results will likely be different for higher *target model* quants, which I can't test myself due to VRAM limitations.


1	+ Qwen3.6 27B DFlash GGUF


2
3	+ llama.cpp quantizations of [z-lab DFlash draft model](https://huggingface.co/z-lab/Qwen3.6-27B-DFlash) for [Qwen3.6 27B](https://huggingface.co/Qwen/Qwen3.6-27B).