Instructions to use quant-mind/Huihui-Nex-N2-mini-abliterated-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 quant-mind/Huihui-Nex-N2-mini-abliterated-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 quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF: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 quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF: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 quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF: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 quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "quant-mind/Huihui-Nex-N2-mini-abliterated-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": "quant-mind/Huihui-Nex-N2-mini-abliterated-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/quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF:UD-Q4_K_XL

Ollama
How to use quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF with Ollama:
```
ollama run hf.co/quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF:UD-Q4_K_XL
```
Unsloth Desktop

How to use quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF: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": "quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF:UD-Q4_K_XL
```

Lemonade

How to use quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Huihui-Nex-N2-mini-abliterated-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use quant-mind/Huihui-Nex-N2-mini-abliterated-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 quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF: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 quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF: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 "quant-mind/Huihui-Nex-N2-mini-abliterated-GGUF: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"

quant-mind commited on Jun 22

Commit

22be29b

verified ·

1 Parent(s): 5087d1b

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +13 -30

README.md CHANGED Viewed

@@ -2,41 +2,24 @@
 base_model: huihui-ai/Huihui-Nex-N2-mini-abliterated
 license: apache-2.0
 pipeline_tag: image-text-to-text
-tags:
-- gguf
-- llama.cpp
-- multimodal
-- vision
-- abliterated
-- uncensored
-- qwen3_5_moe
 ---
 # Huihui-Nex-N2-mini-abliterated-GGUF
-GGUF de [`huihui-ai/Huihui-Nex-N2-mini-abliterated`](https://huggingface.co/huihui-ai/Huihui-Nex-N2-mini-abliterated) (arch `qwen3_5_moe`, MoE ~35B, **multimodal**),
-convertido com `llama.cpp` (`convert_hf_to_gguf.py` + `llama-quantize`).
-## Arquivos
-| Arquivo | Tamanho | Descrição |
-|---|---|---|
-| `Huihui-Nex-N2-mini-abliterated-Q4_K_M.gguf` | ~20 GB | LLM (texto) quantizado em **Q4_K_M** |
-| `mmproj-Huihui-Nex-N2-mini-abliterated-f16.gguf` | ~858 MB | **Projetor de visão** (mmproj, f16) — necessário para entrada de imagem |
-## Uso (visão) com llama.cpp
-Os dois arquivos são necessários para multimodalidade. Exemplo:
 ```bash
-# servidor com suporte a imagem
-llama-server \
-  -m Huihui-Nex-N2-mini-abliterated-Q4_K_M.gguf \
-  --mmproj mmproj-Huihui-Nex-N2-mini-abliterated-f16.gguf \
-  -c 8192 --host 0.0.0.0 --port 8080
-# CLI multimodal
-llama-mtmd-cli \
-  -m Huihui-Nex-N2-mini-abliterated-Q4_K_M.gguf \
-  --mmproj mmproj-Huihui-Nex-N2-mini-abliterated-f16.gguf \
-  --image foto.jpg -p "Descreva a imagem."
 ```
-> Requer um build recente do llama.cpp (suporte a `qwen3_5_moe` + torre de visão Qwen3-VL).

 base_model: huihui-ai/Huihui-Nex-N2-mini-abliterated
 license: apache-2.0
 pipeline_tag: image-text-to-text
+tags: [gguf, llama.cpp, multimodal, vision, abliterated, qwen3_5_moe, imatrix]
 ---
 # Huihui-Nex-N2-mini-abliterated-GGUF
+GGUF de [`huihui-ai/Huihui-Nex-N2-mini-abliterated`](https://huggingface.co/huihui-ai/Huihui-Nex-N2-mini-abliterated) (arch `qwen3_5_moe`, MoE ~35B, **multimodal**), via `llama.cpp`.
+> Conversao corrigida: o `block_count` (camada MTP/nextn fantasma) foi ajustado de 41 para 40 para o modelo carregar.
+## Arquivos
+| Arquivo | O que e |
+|---|---|
+| `Huihui-Nex-N2-mini-abliterated-UD-Q4_K_XL.gguf` | LLM texto **Q4_K_M + imatrix** (din., estilo Unsloth UD) |
+| `Huihui-Nex-N2-mini-abliterated-Q4_K_M.gguf` | LLM texto Q4_K_M padrao |
+| `mmproj-Huihui-Nex-N2-mini-abliterated-f16.gguf` | **Projetor de visao** (necessario p/ imagem) |
+| `imatrix-Huihui-Nex-N2-mini-abliterated.dat` | importance matrix (calibration_datav3) |
+## Uso (visao)
 ```bash
+llama-server -m Huihui-Nex-N2-mini-abliterated-UD-Q4_K_XL.gguf \
+  --mmproj mmproj-Huihui-Nex-N2-mini-abliterated-f16.gguf -c 8192
 ```