Qwen3 8B
Qwen3-8B is a causal language model from the Qwen series, developed by the Qwen team. It is an 8.2B parameter model (6.95B non-embedding) with 36 layers and grouped-query attention (32 query heads, 8 key/value heads). The model supports text generation and is designed for both thinking and non-thinking modes within a single model. It has a native context length of 32,768 tokens, extendable to 131,072 tokens with YaRN. The model card highlights advancements in reasoning, instruction-following, agent capabilities, and multilingual support (100+ languages). It is licensed under Apache-2.0 and built on Qwen/Qwen3-8B-Base.
What do you want to do?
Choose a task. Get the software, files, settings, and steps to run it.
Create Uncensored AI Bots with Rakazo
Create persistent Rakazo bots with Huihui’s uncensored Qwen3 8B. Choose local Ollama or the documented 48 GB RunPod Serverless Load Balancer vLLM setup.
Build a local AI agent team with Qwen3 8B
Build a local AI agent team with Qwen3 8B, Ollama and CrewAI. The example assigns reader, writer and reviewer roles to compare two product briefs, with source reads, task handoffs and a final Markdown file you can inspect.
Build a local AI tool agent with Qwen3 8B
Run a bounded local function through Qwen3 8B and inspect the tool call, tool result, and final answer.
Open a guide for its software, hardware requirements, and setup steps.
Uncensored versions
Qwen3 8B · Abliterated
By Huihui AIA community uncensored version of Qwen3 8B, modified using abliteration to reduce refusals.
View on Hugging FaceAt a glance
- Parameters
- 8.2B
- Architecture
- Dense transformer
- Context length
- 32,768 native
- License
- Apache 2.0
- Disk space
- 5.2 GB
- Software
- Ollama, llama.cpp
Will it run on your machine?
Save your machine to see a personalized rating and its reasoning.
Add my hardwareBest for
- Complex logical reasoning, mathematics, and coding tasks (thinking mode)
- Efficient general-purpose dialogue and conversation (non-thinking mode)
- Creative writing, role-playing, and multi-turn dialogues
- Agent-based tasks with external tool integration
- Multilingual instruction following and translation
Tradeoffs
- Requires transformers version 4.51.0 or later; older versions cause a KeyError.
- Performance and hardware requirements are not specified in the provided data.
- No benchmark results or evaluation details are included in the source data.
- Actual context length beyond 32,768 tokens requires YaRN, which is not detailed in the source.
- No information on safety, bias, or ethical considerations is provided.
Ways to run it
vLLM · Linux
Repository-specific example documented in the publisher model card; confirm dependencies and platform in the source.
vllm serve Qwen/Qwen3-8B --enable-reasoning --reasoning-parser deepseek_r1Transformers · See official guide
Repository-specific example documented in the publisher model card; confirm dependencies and platform in the source.
from transformers import AutoModelForCausalLM, AutoTokenizer
class QwenChatbot:
def __init__(self, model_name="Qwen/Qwen3-8B"):
self.tokenizer = AutoTokenizer.from_pretrained(model_name)
self.model = AutoModelForCausalLM.from_pretrained(model_name)
self.history = []
def generate_response(self, user_input):
messages = self.history + [{"role": "user", "content": user_input}]
text = self.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
inputs = self.tokenizer(text, return_tensors="pt")
response_ids = self.model.generate(**inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist()
response = self.tokenizer.decode(response_ids, skip_special_tokens=True)
# Update history
self.history.append({"role": "user", "content": user_input})
self.history.append({"role": "assistant", "content": response})
return response
# Example Usage
if __name__ == "__main__":
chatbot = QwenChatbot()
# First input (without /think or /no_think tags, thinking mode is enabled by default)
user_input_1 = "How many r's in strawberries?"
print(f"User: {user_input_1}")
response_1 = chatbot.generate_response(user_input_1)
print(f"Bot: {response_1}")
print("----------------------")
# Second input with /no_think
user_input_2 = "Then, how many r's in blueberries? /no_think"
print(f"User: {user_input_2}")
response_2 = chatbot.generate_response(user_input_2)
print(f"Bot: {response_2}")
print("----------------------")
# Third input with /think
user_input_3 = "Really? /think"
print(f"User: {user_input_3}")
response_3 = chatbot.generate_response(user_input_3)
print(f"Bot: {response_3}")Explore its uses
Keep exploring
Bonsai 2 · 27B
A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.
DeepSeek V4.1 Flash
An open-weight model for reasoning, coding, agents, and image understanding. DeepSeek V4.1 Flash combines a 552B backbone with sparse activation and up to one million tokens of context. Choose the original checkpoint or a community uncensored variant below.
Qwen3.8
Explore 4 versions of Qwen3.8. Compare model sizes, packages, hardware requirements, and available setups.