Instructions to use Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-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 Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-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 Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-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 Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-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 Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-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 Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-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": "Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-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/Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF:Q4_K_M

Ollama
How to use Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF with Ollama:
```
ollama run hf.co/Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-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": "Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF with Docker Model Runner:
```
docker model run hf.co/Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF:Q4_K_M
```

Lemonade

How to use Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-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 Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-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 Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-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 "Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-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"

Solstice-AI Banner

Qwen3.8-27B-TURBO NEO-CODER (Official Clean GGUF Suite)

Official Solstice-AI Release • Standard Clean UD 3.0 Matrix • Multi-Token Prediction (MTP) Speculative Tiers • Pure BF16 Multimodal Vision Projector

Original Architecture by Qwen / Alibaba Cloud • Uncensored Weights by DavidAU • Curated & Packaged by Solstice-AI

Model Summary

Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF contains the official clean GGUF suite of Qwen3.8-27B NEO-CODER, bringing DavidAU's latest coding and agentic prompt engineering optimizations into standard, clean UD 3.0 GGUF binaries.

Key NEO-CODER Capabilities:

Dynamic Reasoning Effort Controls (reasoning_effort):
- medium: Suppresses default system prompt injection for direct, unrestricted coding execution and SWE-bench compatibility.
- xhigh: Injects deep-reasoning verification tags (<thought>) for complex algorithmic design and proofs.
Deterministic XML Tool Calling: Pre-configured for <tool_call><function=...><parameter=...></function></tool_call> execution.
Pure BF16 Vision Transformer (mmproj-BF16.gguf): Standalone 16-bit multimodal vision projector with zero FP16 underflow risks.
Multi-Token Prediction (MTP) Speculative Tiers: Bundles specialized MTP models (speculative-mtp/) and DSpark drafters (speculative/).

File Catalog

Filename	Precision / Quant	Size	Recommended Use Case
`Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-Q4_K_M.gguf`	Q4_K_M (UD-Q4_K_XL)	16.81 GB	Recommended: Best balance of speed, RAM footprint & accuracy
`Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-Q5_K_M.gguf`	Q5_K_M	19.31 GB	High-accuracy coding and mathematical reasoning
`Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-Q6_K.gguf`	Q6_K	21.96 GB	Near-lossless weights for complex multi-file refactoring
`Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-Q8_0.gguf`	Q8_0	27.74 GB	Pure lossless 8-bit precision
*`speculative-mtp/-MTP-Q4_K_M.gguf`**	MTP Q4_K_M	17.23 GB	Multi-Token Prediction enabled speculative decoding
*`speculative-mtp/-MTP-Q8_0.gguf`**	MTP Q8_0	28.16 GB	Lossless MTP speculative decoding
`mmproj-BF16.gguf`	Pure BF16	0.87 GB	Official standalone Multimodal Vision Projector
`speculative/Qwen3.8-27B-DSpark-Q4_K_M.gguf`	DSpark Drafter	1.03 GB	Ultra-fast pre-aligned speculative draft model

Quickstart with `llama.cpp`

Standard Multimodal Inference:

llama-server \
  -m Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-Q4_K_M.gguf \
  --mmproj mmproj-BF16.gguf \
  -c 131072 \
  --port 8080

Speculative Decoding (1.8x Speedup):

llama-cli \
  -m Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-Q4_K_M.gguf \
  -md speculative/Qwen3.8-27B-DSpark-Q4_K_M.gguf \
  --mmproj mmproj-BF16.gguf \
  -p "Write a high-performance async actor pool in Rust using Tokio."

Downloads last month: 389

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Model tree for Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF

Base model

Qwen/Qwen3.8-27B

Finetuned

DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU

Quantized

(54)

this model

Qwen3.8-27B-TURBO NEO-CODER (Official Clean GGUF Suite)

Official Solstice-AI Release • Standard Clean UD 3.0 Matrix • Multi-Token Prediction (MTP) Speculative Tiers • Pure BF16 Multimodal Vision Projector

Model Summary

Key NEO-CODER Capabilities:

File Catalog

Quickstart with llama.cpp

Standard Multimodal Inference:

Speculative Decoding (1.8x Speedup):

Model tree for Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-NEO-CODER-GGUF

Quickstart with `llama.cpp`