Instructions to use jakeatx/Qwen3.8-Perian-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 jakeatx/Qwen3.8-Perian-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 jakeatx/Qwen3.8-Perian-GGUF
# Run inference directly in the terminal:
llama cli -hf jakeatx/Qwen3.8-Perian-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jakeatx/Qwen3.8-Perian-GGUF
# Run inference directly in the terminal:
llama cli -hf jakeatx/Qwen3.8-Perian-GGUF

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 jakeatx/Qwen3.8-Perian-GGUF
# Run inference directly in the terminal:
./llama-cli -hf jakeatx/Qwen3.8-Perian-GGUF

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 jakeatx/Qwen3.8-Perian-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jakeatx/Qwen3.8-Perian-GGUF

Use Docker

docker model run hf.co/jakeatx/Qwen3.8-Perian-GGUF

LM Studio
Jan

vLLM

How to use jakeatx/Qwen3.8-Perian-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jakeatx/Qwen3.8-Perian-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": "jakeatx/Qwen3.8-Perian-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jakeatx/Qwen3.8-Perian-GGUF

Ollama
How to use jakeatx/Qwen3.8-Perian-GGUF with Ollama:
```
ollama run hf.co/jakeatx/Qwen3.8-Perian-GGUF
```
Unsloth Desktop

How to use jakeatx/Qwen3.8-Perian-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jakeatx/Qwen3.8-Perian-GGUF

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": "jakeatx/Qwen3.8-Perian-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jakeatx/Qwen3.8-Perian-GGUF with Docker Model Runner:
```
docker model run hf.co/jakeatx/Qwen3.8-Perian-GGUF
```

Lemonade

How to use jakeatx/Qwen3.8-Perian-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jakeatx/Qwen3.8-Perian-GGUF

Run and chat with the model

lemonade run user.Qwen3.8-Perian-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use jakeatx/Qwen3.8-Perian-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 jakeatx/Qwen3.8-Perian-GGUF

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 jakeatx/Qwen3.8-Perian-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jakeatx/Qwen3.8-Perian-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jakeatx/Qwen3.8-Perian-GGUF

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 "jakeatx/Qwen3.8-Perian-GGUF" \
  --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 Perian GGUF

Qwen3.8 Perian is a deliberately compressed and post-trained Qwen3.8-Flash-Next lineage. It combines depth pruning, routed-expert width reduction, and a document-disjoint, activation-informed reduction of the PLE n-gram table, then adds a rank-32 QLoRA trained on frontier-model reasoning trajectories.

What was reduced

Depth: 48 transformer layers were reduced to 32 (16 layers removed; 33.3% fewer layers).
Routed-expert width: 384 experts per layer were merged to 288 (96 fewer expert slots per layer; 25% reduction), while retaining 10 selected experts per token. The merge used layer-local router, similarity, and activation saliency evidence from 1,024 calibration sequences of 512 tokens, weighted toward tool use, executable code, retrieval, and multi-step reasoning.
PLE n-gram capacity: 320,001,446 rows were reduced to 160,000,768 rows (50%). This removed about 25.60B parameters. The frozen selection combined activation-aware bigram heads 0-7 with frequency-ranked trigram heads 8-15 and was validated on a document-disjoint 5M-token holdout.

The resulting compact BF16 base contains 74,615,655,680 parameters and 150,511,416,232 tensor bytes before GGUF quantization.

QLoRA post-training

The compact model was post-trained with rank-32 QLoRA on 12,558 normalized traces covering coding and debugging, mathematics and STEM reasoning, agentic/tool-use trajectories, retrieval, and general multi-step reasoning. The mixture contains traces produced by several frontier model families, including Fable 5, GLM 5.2, Kimi K3, Claude Opus 4.7, Qwen3.8-Max, and GPT-5.6-Sol. Assistant reasoning, answers, tool calls, and end-of-message tokens were supervised; prompts, tool definitions/results, and repeated context were masked. The merged checkpoint used here is the rank-32 milestone at 9,336,692 supervised assistant tokens.

The private normalized training corpus has 25,811,891 canonical rendered tokens and 10,299,662 canonical supervised tokens. It remains private because its upstream records do not share one uniform license or blanket downstream-use clearance. The adapter source is jakeatx/ream-288-rank32-3m-adapter at revision 41947bd12f74482906995f47b5c8a7c5703cfca1, path milestones/checkpoint-wall-9336692/adapter.

Files

File	Size	SHA-256	Recipe
`Qwen3.8-Perian-UD-Q4-K-XS.gguf`	44,842,893,088 bytes (44.84 GB)	`70896b81fe0c4c24757a6df4344ec28c133a8c1893573227c1fe5593fcc89058`	Unsloth `UD-Q3_K_XL` tensor recipe with every IQ2/IQ3 XS-family assignment promoted to `IQ4_XS`.
`Qwen3.8-Perian-Q4-K-M.gguf`	51,589,880,608 bytes (51.59 GB)	`9e40972ffa1248543616dc915555dca8f412100135507b43d8dc95d97bf48def`	Standard llama.cpp control.
`Qwen3.8-Perian-UD-Q5-K-XL.gguf`	69,482,800,928 bytes (69.48 GB)	`9d22ba116ad68b3d2f018247c7299cc7b8e1a386b79a5de7e093d4dfc1f6c6d6`	Current Unsloth Qwen3.8 tensor assignments for retained blocks 0-31.
`Qwen3.8-Perian-Q8-0.gguf`	80,656,975,648 bytes (80.66 GB)	`e71c7e0e840bb4fe6e4d5684a412ee9e9c5d7cb029640ebe4555219e50e34d52`	Standard high-fidelity control.

The GGUF converter and quantizer use a pinned, patched qwen4exp llama.cpp build that preserves the compact PLE remap tensor as integer metadata. A compatible runtime must understand the qwen4exp architecture and compact PLE remap.

Status and limitations

The GGUFs do not yet include a validated MTP draft head. Treat MTP attachment as a separate runtime-compatibility milestone rather than assuming the draft head from the unpruned 48-layer model is compatible with this 32-layer trunk. The pruning, holdout, merge, and training gates passed, but these artifacts should still be evaluated on the target runtime and benchmark suite before a production deployment decision.