Qwen3 14B Base Unsloth Bnb 4bit by unsloth

 ยป  All LLMs  ยป  unsloth  ยป  Qwen3 14B Base Unsloth Bnb 4bit   URL Share it on

  Arxiv:2505.09388   4-bit   4bit   Autotrain compatible Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-14b-base   Bitsandbytes   Endpoints compatible   Quantized   Qwen3   Region:us   Safetensors   Sharded   Tensorflow   Unsloth

Qwen3 14B Base Unsloth Bnb 4bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 14B Base Unsloth Bnb 4bit (unsloth/Qwen3-14B-Base-unsloth-bnb-4bit)
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen3 14B Base Unsloth Bnb 4bit Parameters and Internals

LLM NameQwen3 14B Base Unsloth Bnb 4bit
Repository ๐Ÿค—https://huggingface.co/unsloth/Qwen3-14B-Base-unsloth-bnb-4bit 
Base Model(s)  Qwen3 14B Base   Qwen/Qwen3-14B-Base
Model Size14b
Required VRAM10.8 GB
Updated2025-07-24
Maintainerunsloth
Model Typeqwen3
Model Files  5.0 GB: 1-of-3   4.2 GB: 2-of-3   1.6 GB: 3-of-3
Quantization Type4bit
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.52.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 14B Base Unsloth Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 14B Unsloth Bnb 4bit40K / 11.2 GB699008
Qwen3 14B MLX 4bit40K / 8.3 GB452184
Bee1reason Arabic Qwen 14B40K / 29.5 GB119713
Bee1reason Arabic Qwen 14B40K / 29.5 GB5848
Qwen3 14B MLX 4bit40K / 7.9 GB4952
Qwen3 14B 4bit DWQ 05312540K / 8.3 GB1682
Qwen3 14B MLX 8bit40K / 15.2 GB2362
Qwen3 Codellm40K / 29.5 GB230
Qwen3 14B 128K GGUF128K / 3.9 GB401316
Qwen3 14B40K / 29.7 GB782578216
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-14B-Base-unsloth-bnb-4bit.

Rank the Qwen3 14B Base Unsloth Bnb 4bit 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