Qwen3 8B by Qwen

 ยป  All LLMs  ยป  Qwen  ยป  Qwen3 8B   URL Share it on

  Arxiv:2309.00071   Arxiv:2505.09388   Autotrain compatible Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-8b-base   Conversational   Endpoints compatible   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/Qwen/Qwen3-8B 

Qwen3 8B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 8B (Qwen/Qwen3-8B)
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen3 8B Parameters and Internals

LLM NameQwen3 8B
Repository ๐Ÿค—https://huggingface.co/Qwen/Qwen3-8B 
Base Model(s)  Qwen3 8B Base   Qwen/Qwen3-8B-Base
Model Size8b
Required VRAM16.4 GB
Updated2025-07-25
MaintainerQwen
Model Typeqwen3
Model Files  4.0 GB: 1-of-5   4.0 GB: 2-of-5   4.0 GB: 3-of-5   3.2 GB: 4-of-5   1.2 GB: 5-of-5
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen3 8B

Model
Likes
Downloads
VRAM
Qwen3 8B AWQ13729016 GB
Qwen3 8B GGUF59204232 GB
Qwen3 8B Unsloth Bnb 4bit8791097 GB
Qwen3 8B Bnb 4bit167076 GB
Qwen3 8B 128K GGUF1629132 GB
Qwen3 8B 4bit522884 GB
Qwen3 8B 4bit DWQ29494 GB
Qwen3 8B 6bit39796 GB
Qwen3 8B 8bit28998 GB

Best Alternatives to Qwen3 8B

Best Alternatives
Context / RAM
Downloads
Likes
...n3 8B 320K Context 10X Massive320K / 16.4 GB290
Qwen3 8B 256K Context 8X Grand256K / 16.4 GB3090
...wen3 8B 192K Context 6X Larger192K / 16.4 GB200
DeepSeek R1 0528 Qwen3 8B128K / 16.4 GB296445886
DeepSeek R1 0528 Qwen3 8B128K / 16.4 GB431314
...1 0528 Qwen3 8B Abliterated V1128K / 16.4 GB99426
...1 Qwen3 8B ArliAI RpR V4 Small128K / 16.4 GB102816
RPT DeepSeek R1 0528 Qwen3 8B128K / 16.4 GB4432
DeepSeek R1 0528 Qwen3 8B Bf16128K / 16.3 GB11132
OPC R1 8B128K / 16.4 GB2793
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-8B.

Rank the Qwen3 8B Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 50035 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124