Instructions to use anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 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 anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0
# Run inference directly in the terminal:
llama cli -hf anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0
# Run inference directly in the terminal:
llama cli -hf anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0

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 anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0
# Run inference directly in the terminal:
./llama-cli -hf anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0

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 anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0

Use Docker

docker model run hf.co/anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0

LM Studio
Jan

vLLM

How to use anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0

Ollama
How to use anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 with Ollama:
```
ollama run hf.co/anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0
```

Unsloth Studio

How to use anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 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 anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 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 anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 to start chatting

How to use anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0

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": "anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 with Docker Model Runner:
```
docker model run hf.co/anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0
```

Lemonade

How to use anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0

Run and chat with the model

lemonade run user.Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0

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 anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0

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 "anemll/Qwen3.8-2.4T-A95B-FlashMoE-UD-Q1_0" \
  --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"

anemll commited on 9 days ago

Commit

a701e8e

verified ·

1 Parent(s): 184e946

Reference Qwen3.8 source branch

Browse files

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -23,9 +23,10 @@ SSD-backed Flash-MoE package for **Qwen3.8-2.4T-A95B**, exported from the
 This is not a conventional standalone GGUF. The non-routed and shared tensors
 are stored in `model-dense.gguf`; routed expert tensors are stored separately in
 a layer-major `sidecar/` and loaded into a per-layer resident slot bank on demand.
-Use the Flash-MoE-enabled `anemll-flash-llama.cpp` runtime. Stock `llama.cpp`
-builds that do not understand this package layout or its `IQ1_XXXS` routed
-experts cannot run it.
 ## Model and package details
@@ -130,7 +131,8 @@ Important runtime choices:
 - Base model: [Qwen/Qwen3.8-2.4T-A95B](https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B)
 - Source quantization: [unsloth/Qwen3.8-2.4T-A95B-GGUF, UD-Q1_0](https://huggingface.co/unsloth/Qwen3.8-2.4T-A95B-GGUF/tree/main/UD-Q1_0)
-- Flash-MoE packaging/runtime: ANEMLL `anemll-flash-llama.cpp`
 The embedded GGUF metadata reports `license: other`. Review and comply with the
 base model and source repository license terms before use or redistribution.

 This is not a conventional standalone GGUF. The non-routed and shared tensors
 are stored in `model-dense.gguf`; routed expert tensors are stored separately in
 a layer-major `sidecar/` and loaded into a per-layer resident slot bank on demand.
+Use the Flash-MoE-enabled [`Qwen3.8` branch of
+`anemll-flash-llama.cpp`](https://github.com/Anemll/anemll-flash-llama.cpp/tree/Qwen3.8).
+Stock `llama.cpp` builds that do not understand this package layout or its
+`IQ1_XXXS` routed experts cannot run it.
 ## Model and package details
 - Base model: [Qwen/Qwen3.8-2.4T-A95B](https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B)
 - Source quantization: [unsloth/Qwen3.8-2.4T-A95B-GGUF, UD-Q1_0](https://huggingface.co/unsloth/Qwen3.8-2.4T-A95B-GGUF/tree/main/UD-Q1_0)
+- Flash-MoE packaging/runtime: [ANEMLL `anemll-flash-llama.cpp`, `Qwen3.8`
+  branch](https://github.com/Anemll/anemll-flash-llama.cpp/tree/Qwen3.8)
 The embedded GGUF metadata reports `license: other`. Review and comply with the
 base model and source repository license terms before use or redistribution.