Instructions to use rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-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 rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-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 rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-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 rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-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 rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-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 rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M

Use Docker

docker model run hf.co/rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-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": "rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M

Ollama
How to use rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF with Ollama:
```
ollama run hf.co/rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M
```
Unsloth Desktop

How to use rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-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": "rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF with Docker Model Runner:
```
docker model run hf.co/rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M
```

Lemonade

How to use rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-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 rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-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 rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-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 "rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-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-Claude-Opus-Reasoning-Distilled-GGUF

GGUF quantizations of rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled — a LoRA fine-tune of Qwen/Qwen3.8-27B distilled on reasoning traces from Claude Opus 4.6/4.7, merged to 16-bit and quantized for local inference with llama.cpp / Ollama / LM Studio.

MTP (Multi-Token Prediction) head verified working for self-speculative decoding — see below, ~1.6× speedup.

🧠 What this is

Qwen3.8-27B is natively vision-language with a hybrid attention stack (16/64 full-attention layers, 48/64 Gated DeltaNet/linear-attention layers) plus a Multi-Token Prediction head. This fine-tune targets only the text reasoning path; the vision tower is present in the merge (unmodified base weights) but was not targeted by LoRA.

Base model: Qwen/Qwen3.8-27B (dense, 27B, hybrid linear+full attention, MTP head)
Method: LoRA (r=32, alpha=32) via Unsloth, merged to 16-bit, converted with llama.cpp (latest build — required for hybrid Gated DeltaNet operator support)
Training data: ~21.5K examples combining real Opus extended-thinking traces and reconstructed-reasoning traces over genuine Opus outputs (see Dataset Composition below)

📚 Dataset Composition

Source	Examples	What it is
lordx64/reasoning-distill-claude-opus-4-7-max	8,124	Genuine Claude Opus 4.7 extended-thinking traces (verified `model`/`usage` fields per row)
Jackrong/Claude-opus-4.7-TraceInversion-5000x	4,800	Real Opus 4.7 outputs (`teacher_model` field), reasoning trace reconstructed post-hoc by a smaller "trace inversion" model
Jackrong/Claude-opus-4.6-TraceInversion-9000x	8,700	Same trace-inversion method, Opus 4.6

Transparency note: 62% of the dataset has a genuine final answer from Opus but a reconstructed reasoning trace, not Opus's actual internal thinking. The lordx64 subset (38%) is the closest to authentic Opus thinking style. Full details on the base LoRA repo.

⚡ MTP / Speculative Decoding

The Multi-Token Prediction head from the base model (blk.64.nextn.*) survives the LoRA merge and GGUF conversion intact and is functional for self-speculative decoding — verified on Q8_0:

Mode	Generation speed (H100 NVL)
Standard decoding	64.6 tok/s
`--spec-type draft-mtp`	104.2 tok/s (~1.6× speedup)

llama-cli -m qwen3.8-27b-opus-distill.Q8_0.gguf -p "your prompt" -ngl 99 --spec-type draft-mtp

No separate draft model needed — the MTP head inside this same GGUF file acts as the draft. Output quality is unaffected (MTP proposes candidate tokens that the main model verifies; it doesn't change what gets generated, only how fast). Requires a recent llama.cpp build with --spec-type draft-mtp support.

📦 Available Quantizations

File	Size	Notes
`qwen3.8-27b-opus-distill.f16.gguf`	51 GB	Full precision, source for further quantization
`qwen3.8-27b-opus-distill.Q8_0.gguf`	28 GB	Near-lossless, recommended if VRAM allows
`qwen3.8-27b-opus-distill.Q6_K.gguf`	21 GB	Good quality/size trade-off
`qwen3.8-27b-opus-distill.Q5_K_M.gguf`	19 GB
`qwen3.8-27b-opus-distill.Q4_K_M.gguf`	16 GB	Practical for single consumer GPU (24GB card)

All quants verified to generate coherent output (Q8_0 sanity-tested with a technical prompt before upload). MTP speculative decoding available on all quants sharing the same architecture.

⚠️ Requires a recent llama.cpp build. This model uses Qwen3.8's hybrid Gated DeltaNet + Gated Attention architecture — older llama.cpp builds will not load it correctly. Build from source (main branch) if your package manager's version is stale.

🚀 Usage

llama.cpp

./llama-cli -m qwen3.8-27b-opus-distill.Q8_0.gguf -p "Explain the difference between TCP and UDP." -ngl 99 --temp 1.0 --top-p 0.95 --top-k 20

With MTP speculative decoding (faster, same output distribution):

./llama-cli -m qwen3.8-27b-opus-distill.Q8_0.gguf -p "Explain the difference between TCP and UDP." -ngl 99 --temp 1.0 --top-p 0.95 --top-k 20 --spec-type draft-mtp

Ollama / LM Studio

Download the .gguf file matching your VRAM budget from the Files tab and point Ollama/LM Studio at it directly (Modelfile/import instructions per their respective docs).

Thinking is on by default (<think>...</think> block before the final answer), matching the base Qwen3.8 chat template.

⚠️ Known Limitations

This checkpoint is a pipeline-validation run (150 steps, ~12.6% of one epoch), not a fully converged fine-tune. Expect it to show the target <think> format and some stylistic shift, but not robust generalization across task domains.
Dataset partially composed of reconstructed (not captured) reasoning traces — see Dataset Composition above
Text-only fine-tune; vision tower weights are present in the merge (unmodified base) but untested/unused in this GGUF export
Requires latest llama.cpp for hybrid attention + MTP support (see note above)

🙏 Acknowledgments

Training methodology based on the Jackrong fine-tuning guide. Thanks to lordx64 and Jackrong for the source reasoning datasets, and the llama.cpp team for hybrid-architecture support.

Maintained by rico03

Downloads last month: 11,432

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF

Base model

Qwen/Qwen3.8-27B

Adapter

(56)

this model

Datasets used to train rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF

Collection including rico03/Qwen3.8-27B-Claude-Opus-Reasoning-Distilled-GGUF

Qwen3.8-Opus-Reasoning-Distilled

Collection

Collection of Qwen3.6' models fine-tuned with opus • 2 items • Updated 18 days ago • 1