Instructions to use fwizzer1/Fwizzer-R1-3B-RU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use fwizzer1/Fwizzer-R1-3B-RU 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 fwizzer1/Fwizzer-R1-3B-RU
# Run inference directly in the terminal:
llama cli -hf fwizzer1/Fwizzer-R1-3B-RU

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf fwizzer1/Fwizzer-R1-3B-RU
# Run inference directly in the terminal:
llama cli -hf fwizzer1/Fwizzer-R1-3B-RU

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 fwizzer1/Fwizzer-R1-3B-RU
# Run inference directly in the terminal:
./llama-cli -hf fwizzer1/Fwizzer-R1-3B-RU

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 fwizzer1/Fwizzer-R1-3B-RU
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fwizzer1/Fwizzer-R1-3B-RU

Use Docker

docker model run hf.co/fwizzer1/Fwizzer-R1-3B-RU

LM Studio
Jan

vLLM

How to use fwizzer1/Fwizzer-R1-3B-RU with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fwizzer1/Fwizzer-R1-3B-RU"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fwizzer1/Fwizzer-R1-3B-RU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fwizzer1/Fwizzer-R1-3B-RU

Ollama
How to use fwizzer1/Fwizzer-R1-3B-RU with Ollama:
```
ollama run hf.co/fwizzer1/Fwizzer-R1-3B-RU
```
Unsloth Desktop
Docker Model Runner
How to use fwizzer1/Fwizzer-R1-3B-RU with Docker Model Runner:
```
docker model run hf.co/fwizzer1/Fwizzer-R1-3B-RU
```

Lemonade

How to use fwizzer1/Fwizzer-R1-3B-RU with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fwizzer1/Fwizzer-R1-3B-RU

Run and chat with the model

lemonade run user.Fwizzer-R1-3B-RU-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

Fwizzer-R1-3B-RU / README.md

fwizzer1

Update README with Speed and Max filenames

b34cc3e verified 29 days ago

preview code

Raw History Blame Contribute Delete

2.21 kB

	---
	language:
	- ru
	- en
	license: apache-2.0
	tags:
	- reasoning
	- deepseek-r1
	- ru-deepthink-11k
	- mistral
	- text-generation
	- gguf
	pipeline_tag: text-generation
	---

	# 🧠 Fwizzer-R1-3B-RU

	Fwizzer-R1-3B-RU — это мыслящая русскоязычная языковая модель, обученная по архитектуре пошаговых рассуждений (DeepSeek-R1 CoT) на отборном датасете [`fwizzer1/ru-deepthink-11k`](https://huggingface.co/datasets/fwizzer1/ru-deepthink-11k).

	---

	## ⚡️ Доступные версии GGUF

	\| Файл \| Описание \| Рекомендуемое железо \|
	\| :--- \| :--- \| :--- \|
	\| `Fwizzer-R1-3B-Speed.gguf` \| Быстрая версия (Q4_K_M, 2.15 GB) \| RTX 3050 / Ноутбуки / 16GB RAM \|
	\| `Fwizzer-R1-3B-Max.gguf` \| Максимальная точность (Q8_0, 3.40 GB) \| ПК с 8+ GB VRAM \|

	---

	## 🚀 Использование в LM Studio

	1. Откройте LM Studio.
	2. В строке поиска введите: `Fwizzer-R1-3B-RU`.
	3. Нажмите Download на `Fwizzer-R1-3B-Speed.gguf` или `Fwizzer-R1-3B-Max.gguf`.
	4. Модель готова к работе со шторкой размышлений!

	### Вшитый системный промпт:
	```text
	Ты думающая нейросеть а зовут тебя Fwizzer-R1-3B-RU. Весь ход мыслей и шаги пиши внутри тегов <think>(напиши сначала) и </think>(напиши по окончанию рассуждений), а итоговый ответ — обязательно после них.
	```

	---

	## 💻 Использование через Python (llama-cpp-python)

	```python
	from llama_cpp import Llama

	llm = Llama.from_pretrained(
	repo_id="fwizzer1/Fwizzer-R1-3B-RU",
	filename="Fwizzer-R1-3B-Speed.gguf",
	n_ctx=4096,
	n_gpu_layers=-1,
	flash_attn=True
	)

	response = llm.create_chat_completion(
	messages=[
	{"role": "user", "content": "Привет! Расскажи о себе и реши задачу на логику."}
	]
	)

	print(response["choices"][0]["message"]["content"])
	```