Introducing a new LLM model from Project Fluently. The goal of this model is to improve the base model by training it on diverse datasets. This model is obtained by SFT and GRPO training and step-by-step merging.

Model details

Developed by: @fluently
Model type: Causal Language Models (Qwen3ForCausalLM, LM Transformer)
Number of Parameters: 4.0B
Number of Paramaters (Non-Embedding): 3.6B
Number of Layers: 36
Number of Attention Heads (GQA): 32 for Q and 8 for KV
Context Length: 32,768 natively and 131,072 tokens with YaRN
License: Apache-2.0

Recipe

*The recipe is approximate, there are some inaccuracies.

Strengths

General improvements

Task	Result
Basic Communication	Improved
Translation	Improved
Mathematics	Improved
Physics	Improved
Biology	Improved
Medicine	Improved
Coding	Improved
Agent Functions	Improved

Quickstart

Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.

from transformers 
import AutoModelForCausalLM, AutoTokenizer

model_name = "fluently/FluentlyQwen3-4B"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.

Switching Between Thinking and Non-Thinking Mode

[!TIP] The enable_thinking switch is also available in APIs created by SGLang and vLLM.

`enable_thinking=True`

By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting enable_thinking=True or leaving it as the default value in tokenizer.apply_chat_template, the model will engage its thinking mode.

python

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True  # True is the default value for enable_thinking
)

In this mode, the model will generate think content wrapped in a <think>...</think> block, followed by the final response.

[!NOTE] For thinking mode, use Temperature=0.6, TopP=0.95, TopK=20 and MinP=0 (the default setting in generation_config.json). DO NOT use greedy decoding, as it can lead to performance degradation and endless repetitions.

`enable_thinking=False`

We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency.

python

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False  # Setting enable_thinking=False disables thinking mode
)

In this mode, the model will not generate any think content and will not include a <think>...</think> block.

[!NOTE] For non-thinking mode, we suggest using Temperature=0.7, TopP=0.8, TopK=20, and MinP=0.

Special thanks

🤗 We are grateful for open source resources, technologies and assistance from: