Instructions to use AtomicChat/Qwen3.6-27B-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 AtomicChat/Qwen3.6-27B-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 AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL

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 AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL

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 AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use AtomicChat/Qwen3.6-27B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AtomicChat/Qwen3.6-27B-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": "AtomicChat/Qwen3.6-27B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL

Ollama
How to use AtomicChat/Qwen3.6-27B-GGUF with Ollama:
```
ollama run hf.co/AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL
```
Unsloth Desktop

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL

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": "AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AtomicChat/Qwen3.6-27B-GGUF with Docker Model Runner:
```
docker model run hf.co/AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3.6-27B-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use AtomicChat/Qwen3.6-27B-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 AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL

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 AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL

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 "AtomicChat/Qwen3.6-27B-GGUF:UD-Q4_K_XL" \
  --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"

worthant commited on Jul 22

Commit

227d5b1

verified ·

1 Parent(s): 0bdffb7

forge: regenerate the model card

Browse files

Files changed (1) hide show

README.md +33 -34

README.md CHANGED Viewed

@@ -10,12 +10,11 @@ pipeline_tag: text-generation
 library_name: gguf
 tags:
 - atomic-chat
 - qwen
-- qwen3
 - gguf
-- imatrix
-- quantized
 - llama.cpp
 ---
 <center>
@@ -28,23 +27,24 @@ tags:
 <br/>
-<img src="https://huggingface.co/AtomicChat/qwen36-27b-GGUF/resolve/main/hero.png" alt="Qwen3.6 27B" style="width:420px; max-width:100%; height:auto; margin-bottom:0.6em;"/>
 <div style="display:flex; justify-content:center; gap:0.5em;">
 <a href="https://huggingface.co/Qwen/Qwen3.6-27B"><strong>Base model: Qwen/Qwen3.6-27B</strong></a>
 </div>
 </center>
-**Qwen3.6 27B**, self-quantized to GGUF by [Atomic Chat](https://atomic.chat). Built straight from Qwen's original weights with a per-tensor importance matrix. Runs fully offline.
 ## Highlights
-- **First open-weight Qwen3.6 variant**, following the Qwen3.5 series, with a focus on stability and real-world utility.
-- **Agentic coding** that handles frontend workflows and repository-level reasoning with greater fluency and precision.
-- **Thinking Preservation**, a new option to retain reasoning context from historical messages to streamline iterative development.
-- **Base model is multimodal** (vision encoder); these GGUF quants cover the text path.
-- **262,144-token native context**, extensible up to ~1,010,000 tokens.
-- **Full quant ladder** with an importance matrix on every quant over [`calibration_datav3`](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8).
 > [!NOTE]
 > These GGUFs are **self-quantized from the original weights**, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.
@@ -57,32 +57,33 @@ tags:
 | Property | Value |
 |---|---|
 | Base model | `Qwen/Qwen3.6-27B` |
-| Total parameters | 27B |
 | Layers | 64 |
-| Context length | 262,144 native, extensible up to ~1,010,000 |
-| Architecture | Causal LM with vision encoder (Gated DeltaNet + Gated Attention) |
-| This repo | GGUF quants (imatrix), text path |
 <img src="https://huggingface.co/AtomicChat/qwen36-27b-GGUF/resolve/main/benchmark.png" alt="Qwen3.6 27B benchmark scores" style="width:100%; max-width:900px;"/>
-Scores are Qwen's published results for the base `Qwen/Qwen3.6-27B`. Quantization preserves the large majority of this; `Q4_K_M` and up sit within a point or two of full precision.
 ## Choosing a quant
 | Quant | Size | Notes |
 |---|---|---|
-| `Q2_K` | 10.7 GB | Smallest. Minimal RAM, clear quality drop. |
-| `IQ3_M` | 12.6 GB | Beats Q3 at similar size thanks to imatrix. Best low-RAM pick. |
 | `Q3_K_M` | 13.3 GB | Low quality but usable. |
 | `Q3_K_L` | 14.3 GB | A step above Q3_K_M. |
 | `IQ4_XS` | 15.1 GB | Excellent quality for size. Recommended low-bit. |
-| `Q4_K_S` | 15.6 GB | Compact Q4, fast. |
 | **`Q4_K_M`** | 16.5 GB | **Recommended default. Best balance of size, speed and quality.** |
-| **`UD-Q4_K_XL`** | 17.5 GB | **Dynamic. Embeddings and output kept at Q8_0 for higher quality at a Q4 footprint.** |
-| `Q5_K_S` | 18.7 GB | Higher quality. |
 | `Q5_K_M` | 19.2 GB | Higher quality, low loss. |
-| `Q6_K` | 22.1 GB | Near lossless. |
 | `Q8_0` | 28.6 GB | Effectively lossless, reference quality. |
 > [!TIP]
@@ -101,38 +102,36 @@ Run Qwen3.6 27B locally with:
 | Parameter | Value |
 |---|---|
-| temperature | 0.7 |
-| top_p | 0.8 |
 | top_k | 20 |
 | min_p | 0.0 |
-| presence_penalty | 1.5 |
 | repetition_penalty | 1.0 |
-Qwen's recommended Instruct (non-thinking) settings. Thinking mode for general tasks: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0.
 ## Run in llama.cpp
 ```bash
-git clone https://github.com/ggerganov/llama.cpp
 cmake llama.cpp -B llama.cpp/build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
 cmake --build llama.cpp/build --config Release -j --target llama-cli llama-server
 ```
 ```bash
 ./llama.cpp/build/bin/llama-server \
-    -hf AtomicChat/qwen36-27b-GGUF:UD-Q4_K_XL \
     --jinja -ngl 99 -c 8192 -fa on
 ```
 ## How these were made
 1. Download `Qwen/Qwen3.6-27B` (original weights).
-2. Convert to f16 GGUF with [llama.cpp](https://github.com/ggerganov/llama.cpp).
-3. Build an importance matrix over `calibration_datav3` (100 chunks).
-4. Quantize the full ladder with `--imatrix`.
 5. `UD-Q4_K_XL` additionally pins the token-embedding and output tensors to `Q8_0`.
 ## License
-Released by Qwen under the Apache 2.0 license. Quantized by Atomic Chat.

 library_name: gguf
 tags:
 - atomic-chat
+- qwen3.6
 - qwen
 - gguf
 - llama.cpp
+- quantized
 ---
 <center>
 <br/>
+<img src="https://huggingface.co/AtomicChat/qwen36-27b-GGUF/resolve/main/hero.png" alt="Qwen3.6 27B" style="width:100%; max-width:100%; height:auto; margin-bottom:0.6em;"/>
 <div style="display:flex; justify-content:center; gap:0.5em;">
 <a href="https://huggingface.co/Qwen/Qwen3.6-27B"><strong>Base model: Qwen/Qwen3.6-27B</strong></a>
 </div>
 </center>
+**Qwen3.6 27B**, self-quantized to GGUF by [Atomic Chat](https://atomic.chat). Built straight from Qwen's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline.
 ## Highlights
+- **27.8B parameters**: the weights this repo quantizes.
+- **Context length**: 262,144 tokens (256K), as published by Qwen.
+- **64 layers**: Dense decoder.
+- **Modalities**: the base model handles Text, Image; this repo ships text-only quants, it carries no vision projector.
+- **Full imatrix ladder**: every quant is calibrated with an importance matrix.
+- **Agentic Coding:**: the model now handles frontend workflows and repository-level reasoning with greater fluency and precision.
+- **Thinking Preservation:**: we've introduced a new option to retain reasoning context from historical messages, streamlining iterative development and reducing overhead.
 > [!NOTE]
 > These GGUFs are **self-quantized from the original weights**, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.
 | Property | Value |
 |---|---|
 | Base model | `Qwen/Qwen3.6-27B` |
+| Parameters | 27.8B |
 | Layers | 64 |
+| Context length | 262,144 tokens (256K) |
+| Vocabulary | 248,320 |
+| Modalities | Text, Image in the base model; text only in this repo, it ships no vision projector |
+| Architecture | Dense decoder, 24 attention heads over 4 KV heads, `Qwen3_5ForConditionalGeneration` |
+| This repo | GGUF quants (imatrix). Quants: `Q2_K`, `IQ3_M`, `Q3_K_M`, `Q3_K_L`, `IQ4_XS`, `Q4_K_S`, `Q4_K_M`, `UD-Q4_K_XL`, `Q5_K_S`, `Q5_K_M`, `Q6_K`, `Q8_0` |
 <img src="https://huggingface.co/AtomicChat/qwen36-27b-GGUF/resolve/main/benchmark.png" alt="Qwen3.6 27B benchmark scores" style="width:100%; max-width:900px;"/>
+Scores are Qwen's published results for the base `Qwen/Qwen3.6-27B`, not our own measurements. Quantization preserves the large majority of this; `Q4_K_M` and up stay close to full precision.
 ## Choosing a quant
 | Quant | Size | Notes |
 |---|---|---|
+| `Q2_K` | 10.7 GB | Smallest K-quant. Minimal RAM, clear quality drop. |
+| `IQ3_M` | 12.6 GB | Beats Q3 at a similar size thanks to imatrix. Best low-RAM pick. |
 | `Q3_K_M` | 13.3 GB | Low quality but usable. |
 | `Q3_K_L` | 14.3 GB | A step above Q3_K_M. |
 | `IQ4_XS` | 15.1 GB | Excellent quality for size. Recommended low-bit. |
+| `Q4_K_S` | 15.6 GB | Compact 4-bit, fast. |
 | **`Q4_K_M`** | 16.5 GB | **Recommended default. Best balance of size, speed and quality.** |
+| `UD-Q4_K_XL` | 17.5 GB | Dynamic. Embeddings and output kept at Q8_0 for higher quality at a Q4 footprint. |
+| `Q5_K_S` | 18.7 GB | Higher quality, slightly more compact than Q5_K_M. |
 | `Q5_K_M` | 19.2 GB | Higher quality, low loss. |
+| `Q6_K` | 22.1 GB | Near lossless, noticeably lighter than Q8_0. |
 | `Q8_0` | 28.6 GB | Effectively lossless, reference quality. |
 > [!TIP]
 | Parameter | Value |
 |---|---|
+| temperature | 1.0 |
+| top_p | 0.95 |
 | top_k | 20 |
 | min_p | 0.0 |
 | repetition_penalty | 1.0 |
+Qwen's recommended sampling configuration for `Qwen/Qwen3.6-27B`.
 ## Run in llama.cpp
 ```bash
+git clone https://github.com/ggml-org/llama.cpp
 cmake llama.cpp -B llama.cpp/build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
 cmake --build llama.cpp/build --config Release -j --target llama-cli llama-server
 ```
 ```bash
 ./llama.cpp/build/bin/llama-server \
+    -hf AtomicChat/qwen36-27b-GGUF:Q4_K_M \
     --jinja -ngl 99 -c 8192 -fa on
 ```
 ## How these were made
 1. Download `Qwen/Qwen3.6-27B` (original weights).
+2. Convert to f16 GGUF with [llama.cpp](https://github.com/ggml-org/llama.cpp).
+3. Build an importance matrix over our calibration corpus.
+4. Quantize the ladder with `--imatrix`.
 5. `UD-Q4_K_XL` additionally pins the token-embedding and output tensors to `Q8_0`.
 ## License
+Original model by Qwen, released under the Apache 2.0 license. Full terms: [Apache 2.0](https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE). Quantized by Atomic Chat.