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

Use Docker

docker model run hf.co/barozp/Qwen3.8-27B-Opus-Distill-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use barozp/Qwen3.8-27B-Opus-Distill-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "barozp/Qwen3.8-27B-Opus-Distill-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": "barozp/Qwen3.8-27B-Opus-Distill-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/barozp/Qwen3.8-27B-Opus-Distill-GGUF:Q4_K_M

Ollama
How to use barozp/Qwen3.8-27B-Opus-Distill-GGUF with Ollama:
```
ollama run hf.co/barozp/Qwen3.8-27B-Opus-Distill-GGUF:Q4_K_M
```

Unsloth Studio

How to use barozp/Qwen3.8-27B-Opus-Distill-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 barozp/Qwen3.8-27B-Opus-Distill-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 barozp/Qwen3.8-27B-Opus-Distill-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use barozp/Qwen3.8-27B-Opus-Distill-GGUF with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use barozp/Qwen3.8-27B-Opus-Distill-GGUF with Docker Model Runner:
```
docker model run hf.co/barozp/Qwen3.8-27B-Opus-Distill-GGUF:Q4_K_M
```

Lemonade

How to use barozp/Qwen3.8-27B-Opus-Distill-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull barozp/Qwen3.8-27B-Opus-Distill-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-Opus-Distill-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use barozp/Qwen3.8-27B-Opus-Distill-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 barozp/Qwen3.8-27B-Opus-Distill-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 barozp/Qwen3.8-27B-Opus-Distill-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use barozp/Qwen3.8-27B-Opus-Distill-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf barozp/Qwen3.8-27B-Opus-Distill-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 "barozp/Qwen3.8-27B-Opus-Distill-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"

barozp commited on about 1 hour ago

Commit

c594717

verified ·

1 Parent(s): 45b66c9

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +21 -0

README.md CHANGED Viewed

@@ -36,6 +36,25 @@ with the native vision tower and native MTP head carried over untouched.
 - **imatrix-calibrated.** All quants below Q3_K_M use an importance matrix
   built from the model's own reasoning-distillation data (see [Imatrix](#imatrix)).
 ## Quality benchmarks (of the source safetensors model)
 Measured with `lm-evaluation-harness`: **0-shot, loglikelihood (multiple-choice),
@@ -169,3 +188,5 @@ llama-cli -m Qwen3.8-27B-Opus-Distill-Q4_K_M.gguf -no-cnv --spec-type draft-mtp
 [Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) (base)
 → [barozp/Qwen3.8-27B-Opus-Distill](https://huggingface.co/barozp/Qwen3.8-27B-Opus-Distill) (LoRA finetune, safetensors)
 → **this repo** (GGUF quantizations)

 - **imatrix-calibrated.** All quants below Q3_K_M use an importance matrix
   built from the model's own reasoning-distillation data (see [Imatrix](#imatrix)).
+## Known issues
+**Reasoning loop under stacked output-format constraints.** Reported by
+[zxbc2023](https://huggingface.co/zxbc2023) ([full writeup, discussion #1](https://huggingface.co/barozp/Qwen3.8-27B-Opus-Distill/discussions/1)).
+Combining `"no prose"` with a second output-format constraint (e.g. `"no
+markdown"` or `"no comments"`) can send this model into a non-converging
+self-verification reasoning loop -- it burns the entire token budget with
+**zero visible output**. Fully deterministic and reproducible at temp=0.
+Root cause: traced to part of the training data being sourced from
+reconstructed (not verbatim) Opus reasoning traces, not a capability gap.
+**Fixed in [barozp/Qwen3.8-27B-Opus-Distill-v2-clean](https://huggingface.co/barozp/Qwen3.8-27B-Opus-Distill-v2-clean)**
+-- retrained on a rebuilt dataset where every row is traced to a verified
+genuine source. If you're hitting this, switch to v2-clean.
+**Workaround if staying on this version:** avoid combining `"no prose"` with
+another format constraint, or raise the generation token budget to >=4096
+for constrained code-gen tasks.
 ## Quality benchmarks (of the source safetensors model)
 Measured with `lm-evaluation-harness`: **0-shot, loglikelihood (multiple-choice),
 [Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) (base)
 → [barozp/Qwen3.8-27B-Opus-Distill](https://huggingface.co/barozp/Qwen3.8-27B-Opus-Distill) (LoRA finetune, safetensors)
 → **this repo** (GGUF quantizations)
+See [Known Issues](#known-issues) above -- if you're hitting the reasoning-loop bug, [barozp/Qwen3.8-27B-Opus-Distill-v2-clean-GGUF](https://huggingface.co/barozp/Qwen3.8-27B-Opus-Distill-v2-clean-GGUF) fixes it.