Instructions to use Chungulus/Qwen3.8-27B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Chungulus/Qwen3.8-27B-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 Chungulus/Qwen3.8-27B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Chungulus/Qwen3.8-27B-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 Chungulus/Qwen3.8-27B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Chungulus/Qwen3.8-27B-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 Chungulus/Qwen3.8-27B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Chungulus/Qwen3.8-27B-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 Chungulus/Qwen3.8-27B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Chungulus/Qwen3.8-27B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/Chungulus/Qwen3.8-27B-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Chungulus/Qwen3.8-27B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Chungulus/Qwen3.8-27B-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": "Chungulus/Qwen3.8-27B-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/Chungulus/Qwen3.8-27B-GGUF:Q4_K_M
- Ollama
How to use Chungulus/Qwen3.8-27B-GGUF with Ollama:
ollama run hf.co/Chungulus/Qwen3.8-27B-GGUF:Q4_K_M
- Unsloth Studio
How to use Chungulus/Qwen3.8-27B-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 Chungulus/Qwen3.8-27B-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 Chungulus/Qwen3.8-27B-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Chungulus/Qwen3.8-27B-GGUF to start chatting
- Pi
How to use Chungulus/Qwen3.8-27B-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Chungulus/Qwen3.8-27B-GGUF:Q4_K_M
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": "Chungulus/Qwen3.8-27B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Chungulus/Qwen3.8-27B-GGUF with Docker Model Runner:
docker model run hf.co/Chungulus/Qwen3.8-27B-GGUF:Q4_K_M
- Lemonade
How to use Chungulus/Qwen3.8-27B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Chungulus/Qwen3.8-27B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Qwen3.8-27B-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Chungulus/Qwen3.8-27B-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 Chungulus/Qwen3.8-27B-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 Chungulus/Qwen3.8-27B-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Chungulus/Qwen3.8-27B-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Chungulus/Qwen3.8-27B-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 "Chungulus/Qwen3.8-27B-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"
Qwen3.8-27B GGUF
This is a vanilla quantization of Qwen/Qwen3.8-27B. It is not a fine-tune,
merge, ablation, alignment change, or chat-template modification. The source
weights are pinned to commit 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0.
The official checkpoint uses Qwen3_5ForConditionalGeneration / qwen3_5 as
its internal architecture identifier. That string does not mean these
weights came from a Qwen3.5 model.
Conversion
{
"algorithm": "llama.cpp stable K-quants and IQ quants from one F16 GGUF",
"bit_width": [
2,
3,
4,
5,
6,
8
],
"group_size": "format_defined",
"calibration_source": "none for K-quants; local representative prompts for IQ variants if required"
}
- Source tensor inventory: 1199 tensors, including 333 vision tensors and 15 source MTP tensors.
- Conversion tool/runtime requirement:
llama.cpp/5f754ea0e2fd21e1213db7ebebfd65d938d9d69c. - Artifact size: 206.295 GB (decimal).
- Expected hardware: Apple Silicon Metal or CPU; 120 GB temporary headroom.
Calibration source: none for K-quants; local representative prompts for IQ variants if required.
Component status
- Text: passed release tests.
- Vision/video: passed deterministic local image tests.
- Tool calling: passed all native XML tool tests.
- MTP: source MTP tensors were retained by the structural gate; this repository does not claim speculative acceleration.
- Chat template, tokenizer, processor, generation config, and special-token IDs: checked against the locked source by the structural gate.
- Quality comparison: passed against the
locked BF16 source using the exact same functional cases. Semantic similarity
uses
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2ate8f8c211226b894fcb81acc59f3b34ba3efd5f42as a measured proxy, not as ground-truth accuracy. - Longest recorded validation prompt: 73 prompt tokens. This is a measured test boundary, not a claim that the architectural maximum was exercised.
Validation results
{
"release_gate": "PASS",
"text": [
true,
true,
true,
true,
true,
true,
true,
true,
true,
true
],
"tools": [
true,
true,
true,
true,
true
],
"vision": [
true,
true,
true
],
"mtp": {
"passed": true,
"acceleration_claimed": false,
"retention_gate": "GGUF tensor and nextn metadata inspection",
"advertise_acceleration": false
},
"bf16_source_comparison": {
"passed": true,
"mean_semantic_similarity": 0.9082151889801026,
"exact_matches": 5,
"measurements": {
"average_generation_tps": 8.600119274947904,
"peak_memory_gb": null,
"artifact_bytes": 206294771716,
"maximum_prompt_tokens_tested": 73,
"loop_rate": 0.0
},
"evaluator": {
"repo_id": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
"revision": "e8f8c211226b894fcb81acc59f3b34ba3efd5f42",
"pooling": "attention-mask mean pooling followed by L2 normalization",
"maximum_tokens": 256
}
},
"bf16_fixed_logit_comparison": "not applicable to the original 30-slot matrix"
}
No acceleration is advertised unless the MTP report contains a measured throughput improvement. Exact measurements are artifact-, prompt-, context-, and hardware-specific.
Inference
git clone https://github.com/ggml-org/llama.cpp && cd llama.cpp
git checkout 5f754ea0e2fd21e1213db7ebebfd65d938d9d69c
cmake -S . -B build -DGGML_METAL=ON -DCMAKE_BUILD_TYPE=Release
cmake --build build --config Release -j
hf download Chungulus/Qwen3.8-27B-GGUF --local-dir ../qwen38-gguf
cd ../qwen38-gguf
../llama.cpp/build/bin/llama-mtmd-cli -m ./Qwen3.8-27B-Q4_K_M.gguf --mmproj ./mmproj-Qwen3.8-27B-F16.gguf -p 'Describe the image.' --image ./image.png
Use the exact source chat-template controls for thinking (enable_thinking,
reasoning_effort, and preserve_thinking) and the native Qwen tool format.
Limitations
Quantization can reduce quality, especially at very low bit widths. Runtime
support for the hybrid Gated DeltaNet/full-attention graph, vision tower,
projector, processor, and MTP component is format-specific. A loader that reads
only a language tensor is not sufficient. Tested context length and resource
measurements are recorded in validation_result.json; untested context lengths
must not be inferred from the architectural maximum.
License and attribution
The parent model and this unmodified quantization are distributed under the source model's Apache-2.0 license. See the official Qwen3.8-27B repository for the upstream model card and attribution.
- Downloads last month
- 68
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Model tree for Chungulus/Qwen3.8-27B-GGUF
Base model
Qwen/Qwen3.8-27B