LLM EXPLORER 59,516 MODELS INDEXED

Qwen2.5 14B Bnb 4bit by unsloth

By unsloth · 108292 downloads
HF Repo ↗ Copy URL

Qwen2.5 14B Bnb 4bit is an open-source language model by unsloth. Features: 14b LLM, VRAM: 9.9GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.21.

  Arxiv:2407.10671   4-bit   4bit   Ara Base model:quantized:qwen/qwen...   Base model:qwen/qwen2.5-14b   Bitsandbytes   Deu   Endpoints compatible   Eng   Fra   Ita   Jpn   Kor   Por   Quantized   Qwen2   Region:us   Rus   Safetensors   Sharded   Spa   Tensorflow   Tha   Unsloth   Vie   Zho
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen2.5-14B-bnb-4bit 

Qwen2.5 14B Bnb 4bit Parameters and Internals

Model Type 
Causal Language Model
Use Cases 
Areas:
Research, Coding, Mathematics, Multilingual Applications
Applications:
Chatbots, Structured Data Understanding, Role-playing Implementations
Primary Use Cases:
instruction following, generating long texts, understanding structured data, generating structured outputs
Limitations:
Not recommended for conversations without further training
Considerations:
Use post-training methods for conversations like SFT, RLHF
Additional Notes 
Supports multilingual capabilities with improved role-play conditions for chatbots.
Supported Languages 
English (high), Chinese (high), French (medium), Spanish (medium), Portuguese (medium), German (medium), Italian (medium), Russian (medium), Japanese (medium), Korean (medium), Vietnamese (medium), Thai (medium), Arabic (medium), other_languages (basic)
Training Details 
Data Sources:
specialized expert models in coding and mathematics
Context Length:
131072
Model Architecture:
transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Use the latest version of 'transformers' to avoid errors.
LLM NameQwen2.5 14B Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Qwen2.5-14B-bnb-4bit 
Base Model(s)  Qwen/Qwen2.5-14B   Qwen/Qwen2.5-14B
Model Size14b
Required VRAM9.9 GB
Updated2026-07-11
Maintainerunsloth
Model Typeqwen2
Model Files  5.0 GB: 1-of-2   4.9 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.49.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 14B Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M 8bit986K / 15.7 GB43012
Qwen2.5 14B Instruct 1M 4bit986K / 8.3 GB3792
...en2.5 14B Instruct 1M Bnb 4bit986K / 9.9 GB952
...B Instruct 1M Unsloth Bnb 4bit986K / 14.3 GB144
Faqih R1 14B Islamic AI128K / 29.6 GB41440
QwQ 14B Math V0.2128K / 29.7 GB14715
Qwen Carpmuscle V0.3128K / 29.7 GB70
...till Qwen 14B Unsloth Bnb 4bit128K / 14.2 GB1141130
Shed Coder 0.2128K / 9.9 GB160
Qwen2.5 14B Unsloth Bnb 4bit128K / 12.1 GB13711
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen2.5-14B-bnb-4bit.