Instructions to use debugdll/Blind-Text-Models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use debugdll/Blind-Text-Models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="debugdll/Blind-Text-Models",
	filename="blind-1.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Transformers

How to use debugdll/Blind-Text-Models with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="debugdll/Blind-Text-Models")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("debugdll/Blind-Text-Models", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use debugdll/Blind-Text-Models 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 debugdll/Blind-Text-Models
# Run inference directly in the terminal:
llama cli -hf debugdll/Blind-Text-Models

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf debugdll/Blind-Text-Models
# Run inference directly in the terminal:
llama cli -hf debugdll/Blind-Text-Models

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 debugdll/Blind-Text-Models
# Run inference directly in the terminal:
./llama-cli -hf debugdll/Blind-Text-Models

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 debugdll/Blind-Text-Models
# Run inference directly in the terminal:
./build/bin/llama-cli -hf debugdll/Blind-Text-Models

Use Docker

docker model run hf.co/debugdll/Blind-Text-Models

LM Studio
Jan

vLLM

How to use debugdll/Blind-Text-Models with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "debugdll/Blind-Text-Models"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "debugdll/Blind-Text-Models",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/debugdll/Blind-Text-Models

SGLang

How to use debugdll/Blind-Text-Models with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "debugdll/Blind-Text-Models" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "debugdll/Blind-Text-Models",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "debugdll/Blind-Text-Models" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "debugdll/Blind-Text-Models",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use debugdll/Blind-Text-Models with Ollama:
```
ollama run hf.co/debugdll/Blind-Text-Models
```
Unsloth Desktop

How to use debugdll/Blind-Text-Models with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf debugdll/Blind-Text-Models

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": "debugdll/Blind-Text-Models"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use debugdll/Blind-Text-Models with Docker Model Runner:
```
docker model run hf.co/debugdll/Blind-Text-Models
```

Lemonade

How to use debugdll/Blind-Text-Models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull debugdll/Blind-Text-Models

Run and chat with the model

lemonade run user.Blind-Text-Models-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use debugdll/Blind-Text-Models with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf debugdll/Blind-Text-Models

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 debugdll/Blind-Text-Models

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use debugdll/Blind-Text-Models with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf debugdll/Blind-Text-Models

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 "debugdll/Blind-Text-Models" \
  --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"

Blind Text Models

A collection of language models from the Blind family. Named for its focus on text tasks — from conversation to content generation.

Current Model (single entry)

Model	Parameters	Quantization	File size	Context	Focus
Blind Text 1 (`blind-1.gguf`)	20.9B (MoE, 32 experts, 4 active)	MXFP4 + Q8_0	11.3 GB	131 072 (128K)	All-purpose assistant, strong at conversation, explanations and generation in Russian and English

Only one model is in the collection for now. New versions will be added to this table.

Architecture

Base architecture: in-house (Blind series)
24 blocks, embedding size 2880
32 experts, 4 active per token
Context up to 128K tokens
Quantization: MXFP4 (expert weights) + Q8_0 (embeddings/output)
Format: GGUF, runs via llama.cpp / Ollama / llama-cpp-python

What It Is Good At

Lively conversation — natural answers, casual and business communication in Russian and English
Explanations — breaks down complex topics clearly
Text generation — letters, posts, articles, concise summaries
Instructions and questions — holds context well, knows how to clarify and answer to the point

The model introduces itself as Blind 1 — that is how it presents itself when asked. This is a build feature.

Hardware / VRAM

Runs fully on GPU in ~11.5 GB — fits comfortably in a 12 GB VRAM card, and easily on 16 GB+. CPU-only inference works too (slower). No external API keys or cloud required — fully local and private.

Benchmarks

Instrumental metrics (MMLU and similar) are still being measured and will be added here. Generation speed is already benchmarked:

Environment	Generation
NVIDIA RTX 5080 (16GB), llama.cpp	≈ 10 tok/s (100 tokens in ~10 s, including the reasoning prefix)

Parameter estimates:

Total parameters: 20 914 757 184 (~20.9B) — counted from the model tensors
Parameters excluding embeddings and output layer: 19.76B

Usage

# llama.cpp
llama-cli -m blind-1.gguf -p "Hello, who are you?"

# llama-cpp-python
from llama_cpp import Llama
llm = Llama(model_path="blind-1.gguf", n_ctx=8192, n_gpu_layers=-1)
print(llm.create_chat_completion(messages=[{"role": "user", "content": "Who are you?"}]))

License

The model is distributed under the Apache 2.0 license.

Downloads last month: 201

GGUF

Model size

21B params

Architecture

gpt-oss

Hardware compatibility

We're not able to determine the quantization variants.

View all variants