LLM EXPLORER 61,405 MODELS INDEXED

Qwen3 14B Bnb 4bit by unsloth

By unsloth · 8512 downloads
HF Repo ↗ Copy URL

Qwen3 14B Bnb 4bit is an open-source language model by unsloth. Features: 14b LLM, VRAM: 9.9GB, Context: 40K, License: apache-2.0, Quantized, LLM Explorer Score: 0.21.

  Arxiv:2309.00071   4-bit   4bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-14b   Bitsandbytes   Quantized   Qwen3   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-14B-bnb-4bit 

Qwen3 14B Bnb 4bit Parameters and Internals

LLM NameQwen3 14B Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Qwen3-14B-bnb-4bit 
Base Model(s)  Qwen3 14B   Qwen/Qwen3-14B
Model Size14b
Required VRAM9.9 GB
Updated2026-08-03
Maintainerunsloth
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   4.9 GB: 2-of-2
Quantization Type4bit
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen3 14B Bnb 4bit

Model
Likes
Downloads
VRAM
Prototie Ai038529 GB

Best Alternatives to Qwen3 14B Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 14B Unsloth Bnb 4bit40K / 11.2 GB18052117
Prototie Ai40K / 29.5 GB3850
Qwen3 14B 4bit40K / 8.3 GB808375
Qwen3 14B MLX 4bit40K / 8.3 GB495366
Qwen3 14B MLX 8bit40K / 15.2 GB164565
Hermes 4 14B 4bit40K / 8.3 GB11225
Hermes 4 14B 8bit40K / 15.7 GB3682
Qwen3 14B MLX 4bit40K / 7.9 GB132814
...wen3 14B Non Thinking V6 16bit40K / 29.5 GB180
Merged16 Sft Qwen340K / 29.5 GB50
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-14B-bnb-4bit.