Instructions to use Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M 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/Qwopus3.8-27B-Flash-GGUF-1M 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/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL

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/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL

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/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL

Use Docker

docker model run hf.co/Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M"
# 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/Qwopus3.8-27B-Flash-GGUF-1M",
		"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/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL

Ollama
How to use Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M with Ollama:
```
ollama run hf.co/Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL
```
Unsloth Desktop

How to use Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M 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/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL

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/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M with Docker Model Runner:
```
docker model run hf.co/Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL
```

Lemonade

How to use Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwopus3.8-27B-Flash-GGUF-1M-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M 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/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL

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/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M 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/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL

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/Qwopus3.8-27B-Flash-GGUF-1M:UD-Q4_K_XL" \
  --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

Qwopus3.8-27B-Flash-1M (GGUF Suite)

Official Solstice-AI Quantization • Native 1M Context Window • Full Multimodal Vision • DSpark Drafters

Model Overview

Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M provides the official, production-grade GGUF suite of Qwopus3.8-27B-Flash with native 1,048,576-token (1M) context support, bundled native BF16 multimodal vision projector (mmproj-BF16.gguf), and companion DSpark drafter.

Key Specifications

Attribute	Specification
Base Model	`Jackrong/Qwopus3.8-27B-Flash`
Architecture	Qwen3.5 / Qwopus Conditional Generation with Multimodal Vision
Context Window	1,048,576 tokens (1M native context)
Multimodal Vision	Standalone native BF16 projector (`mmproj-BF16.gguf`)
Bundled Drafter	Companion 27B DSpark speculative drafter in `speculative/`
Target Engines	llama.cpp, Ollama, LM Studio, Unsloth

Quantization Ladder & File Matrix

Quant File	Size	Memory Fit	Recommendation / Target
`Qwopus3.8-27B-Flash-UD-Q8_K_XL-1M.gguf`	30.15 GB	48GB–64GB+	Near-lossless FP16 reference precision
`Qwopus3.8-27B-Flash-UD-Q6_K_XL-1M.gguf`	23.95 GB	32GB–48GB	Extended 6-bit Unsloth Dynamic v3.0
`Qwopus3.8-27B-Flash-MTP-Q6_K.gguf`	20.89 GB	32GB VRAM	Ideal for 32GB GPUs with long context
`Qwopus3.8-27B-Flash-MTP-Q5_K_M.gguf`	18.19 GB	24GB–32GB	Balanced 5-bit high precision
`Qwopus3.8-27B-Flash-MTP-Q5_K_S.gguf`	17.67 GB	24GB VRAM	Compact 5-bit
`Qwopus3.8-27B-Flash-UD-Q4_K_XL-1M.gguf`	18.42 GB	24GB VRAM	High-accuracy 4-bit Unsloth Dynamic
`Qwopus3.8-27B-Flash-UD-IQ4_XS-1M.gguf`	16.20 GB	16GB–24GB	High throughput / tight VRAM limits
`mmproj-BF16.gguf`	0.87 GB	Vision	Native vision multimodal projector
`speculative/Qwopus3.8-27B-DSpark-Q8_0.gguf`	0.88 GB	Drafter	Speculative decoding companion

Serving Instructions

llama.cpp with DSpark Speculative Decoding & Vision:

llama-cli \
  --hf-repo Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M \
  --hf-file Qwopus3.8-27B-Flash-MTP-Q6_K.gguf \
  --mmproj mmproj-BF16.gguf \
  --draft-model speculative/Qwopus3.8-27B-DSpark-Q8_0.gguf \
  -c 1048576 \
  -ngl 99

Benchmark Highlights & Validation

Evaluated under the standardized benchmark harness:

Benchmark Suite	Discipline	Qwopus3.8-27B-Flash (1M)	Claude Opus 4.6 Max	GPT-4o
SWE-bench Pro	Agentic Software Engineering	61.7%	53.4%	48.9%
LiveCodeBench v6	Algorithmic Problem Solving	90.3%	88.8%	72.8%
QwenSWEBench	Complex Architecture Refactoring	79.0%	63.8%	61.2%
OSWorld-Verified	Desktop & Operating System Automation	84.3%	72.7%	58.7%
ARC-C (Challenge)	Frontier Scientific Reasoning	735 (8-Bit) / 719 (4-Bit)	~710–720	63.8%
Long-Context Needle	256K → 1M Tokens Retrieval	100% (Bit-Exact)	Pass	Pass

Attribution & Acknowledgments

Original Foundation: Jackrong/Qwopus3.8-27B-Flash & Qwen AI
Quantization & Packaging: Solstice-AI

Downloads last month: 3,148

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Model tree for Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M

Base model

Qwen/Qwen3.8-27B

Finetuned

Jackrong/Qwopus3.8-27B-Flash

Quantized

(38)

this model