Instructions to use JetBrains/Qwen3.8-3.6-27B-blend-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 JetBrains/Qwen3.8-3.6-27B-blend-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 JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf JetBrains/Qwen3.8-3.6-27B-blend-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 JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf JetBrains/Qwen3.8-3.6-27B-blend-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 JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf JetBrains/Qwen3.8-3.6-27B-blend-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 JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q4_K_M

Use Docker

docker model run hf.co/JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use JetBrains/Qwen3.8-3.6-27B-blend-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JetBrains/Qwen3.8-3.6-27B-blend-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": "JetBrains/Qwen3.8-3.6-27B-blend-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q4_K_M

Ollama
How to use JetBrains/Qwen3.8-3.6-27B-blend-GGUF with Ollama:
```
ollama run hf.co/JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q4_K_M
```
Unsloth Desktop

How to use JetBrains/Qwen3.8-3.6-27B-blend-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JetBrains/Qwen3.8-3.6-27B-blend-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": "JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use JetBrains/Qwen3.8-3.6-27B-blend-GGUF with Docker Model Runner:
```
docker model run hf.co/JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q4_K_M
```

Lemonade

How to use JetBrains/Qwen3.8-3.6-27B-blend-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-3.6-27B-blend-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use JetBrains/Qwen3.8-3.6-27B-blend-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 JetBrains/Qwen3.8-3.6-27B-blend-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 JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use JetBrains/Qwen3.8-3.6-27B-blend-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JetBrains/Qwen3.8-3.6-27B-blend-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 "JetBrains/Qwen3.8-3.6-27B-blend-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"

Qwen3.8-3.6-27B-blend-GGUF / README.md

vvsotnikov

Add acceptable-use reminder and training provenance statement

6db6fb3 verified 4 days ago

preview code

Raw

History Blame Contribute Delete

6.15 kB

	---
	license: apache-2.0
	base_model: JetBrains/Qwen3.8-3.6-27B-blend
	base_model_relation: quantized
	library_name: gguf
	pipeline_tag: image-text-to-text
	tags:
	- gguf
	- llama.cpp
	- qwen3_5
	- quantized
	- speculative-decoding
	---

	# Qwen3.8-3.6-27B-blend GGUF

	Unofficial JetBrains derivative. This model was prepared by JetBrains using Qwen models developed by Alibaba Cloud. This release is not affiliated with, sponsored by, or endorsed by Alibaba Cloud or Alibaba Group.

	IQ3_S, Q4_K_M, and Q5_K_M conversions of [JetBrains/Qwen3.8-3.6-27B-blend](https://huggingface.co/JetBrains/Qwen3.8-3.6-27B-blend/tree/f1a19acf58aa8caf7a0a507c9083245f79944dcc), pinned to revision `f1a19acf58aa8caf7a0a507c9083245f79944dcc`.

	The base model is a 50/50 combination of Qwen3.6-27B and Qwen3.8-27B, created by linearly interpolating their checkpoint parameters. The configuration, tokenizer, processor, and chat template are retained from Qwen3.8-27B. Exact source revisions and merge settings are recorded in [merge-manifest.json](merge-manifest.json). See [conversion-manifest.json](conversion-manifest.json) for conversion settings and runtime versions.

	\| File \| Size (decimal GB) \| Contents \|
	\|---\|---:\|---\|
	\| `Qwen3.8-3.6-27B-blend-IQ3_S.gguf` \| 12.60 \| Main model plus native MTP head \|
	\| `Qwen3.8-3.6-27B-blend-Q4_K_M.gguf` \| 16.81 \| Main model plus native MTP head \|
	\| `Qwen3.8-3.6-27B-blend-Q5_K_M.gguf` \| 19.54 \| Main model plus native MTP head \|
	\| `mmproj-Qwen3.8-3.6-27B-blend-BF16.gguf` \| 0.93 \| BF16 vision encoder and projector \|

	The MTP head is embedded in each main GGUF. A separate drafter file is not required. The vision GGUF is shared by all three quantizations and is required for image input.

	## Run

	Use a recent llama.cpp with Qwen3.5 native MTP support. The tested revision is `64e9bceb2c3a856efed96feda784a50947049feb`.

	```bash
	llama-server \
	--model Qwen3.8-3.6-27B-blend-Q4_K_M.gguf \
	--mmproj mmproj-Qwen3.8-3.6-27B-blend-BF16.gguf \
	--alias Qwen3.8-3.6-27B-blend \
	--spec-type draft-mtp --spec-draft-n-max 3 \
	--n-gpu-layers 99 --ctx-size 8192 --parallel 2 \
	--jinja --reasoning on --reasoning-format deepseek \
	--chat-template-kwargs '{"enable_thinking":true,"preserve_thinking":true}' \
	--temp 1.0 --top-p 0.95 --top-k 20 --min-p 0 --repeat-penalty 1 \
	--host 127.0.0.1 --port 8080
	```

	Substitute the IQ3_S or Q5_K_M filename to use that quant. API requests should retain the source sampling settings: temperature 1.0, top-p 0.95, top-k 20, with thinking enabled.

	## Conversion

	All three quants were produced directly from one BF16 GGUF intermediate, using llama.cpp's default quantization recipes, without an importance matrix. They were not converted from previously quantized MLX weights.

	```bash
	python convert_hf_to_gguf.py /path/to/pinned-bf16-source \
	--outtype bf16 --outfile model-BF16.gguf
	./build/bin/llama-quantize model-BF16.gguf model-IQ3_S.gguf IQ3_S 10
	./build/bin/llama-quantize model-BF16.gguf model-Q4_K_M.gguf Q4_K_M 10
	./build/bin/llama-quantize model-BF16.gguf model-Q5_K_M.gguf Q5_K_M 10
	python convert_hf_to_gguf.py /path/to/pinned-bf16-source \
	--mmproj --outtype bf16 --outfile mmproj-BF16.gguf
	```

	Environment: Python 3.12.14, PyTorch 2.11.0, Transformers 5.14.0, NumPy 1.26.4; llama.cpp built with Metal on an Apple M5 Max with 128 GiB RAM. Full conversion and validation settings are in `conversion-manifest.json`.

	## Validation

	All three quants retain all 866 main-file tensors, including all 15 MTP tensors, with one next-token-prediction layer declared in the GGUF metadata.

	All three passed local text, image, streaming, two-request concurrency, invalid-request handling, client-disconnect cleanup, and post-cancellation recovery checks on Metal. The image test correctly identified a red square and blue circle. Text responses included separate reasoning content with thinking enabled.

	On the first arithmetic smoke request, Q4_K_M accepted 98/114 drafted tokens (86.0%) and Q5_K_M accepted 78/93 (83.9%). These are individual smoke results, not comparative quality or speed benchmarks. No BF16 parity or broad quality evaluation is claimed.

	IQ3_S was added on 2026-09-15 using the same BF16 intermediate and llama.cpp revision. It passed the same functional checks with thinking and native MTP enabled. Its arithmetic smoke request accepted 113/144 drafted tokens (78.5%). This is a smoke-test observation, not a quality or performance benchmark. The exact artifact SHA256, input SHA256, and validation results are recorded in `conversion-manifest.json`.

	## License and attribution

	Distributed under the Apache License, Version 2.0. The original Qwen [LICENSE](LICENSE), including `Copyright 2026 Alibaba Cloud`, is retained unchanged.

	Copyright © 2026 JetBrains s.r.o. This notice applies only to original material contributed by JetBrains. Upstream Qwen material remains subject to its original copyright and attribution notices.

	See [NOTICE](NOTICE) for attribution and [CHANGES.md](CHANGES.md) for a description of the modifications and the affected files.

	## Note on acceptable use

	This model is distributed under the Apache License, Version 2.0. This notice does not modify the License. Users are reminded that using this model, or its outputs, to infringe the copyright or other intellectual property rights of third parties may violate applicable law, independent of the terms of this License.

	## Training and upstream information

	No additional training or fine-tuning was performed, and no additional training data was used to create this derivative; its preparation consisted of the checkpoint merge and, where applicable, the extraction, format conversion, and quantization described above and in [CHANGES.md](CHANGES.md).

	For upstream information, see the official [Qwen3.6-27B model card](https://huggingface.co/Qwen/Qwen3.6-27B) and [Qwen3.8-27B model card](https://huggingface.co/Qwen/Qwen3.8-27B). Qwen also publishes a [Training Data Summary](https://qwen.ai/training-data-summary), which describes training data for models powering qwen.ai generally; it does not identify the exact training datasets for these two checkpoints.