LLM EXPLORER 59,516 MODELS INDEXED

Qwen2.5 0.5B Instruct Bnb 4bit by unsloth

By unsloth · 14598 downloads
HF Repo ↗ Copy URL

Qwen2.5 0.5B Instruct Bnb 4bit is an open-source language model by unsloth. Features: 0.5b LLM, VRAM: 0.5GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.18.

  Arxiv:2407.10671   4-bit   4bit Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-0.5b-i...   Bitsandbytes   Conversational   Deploy:azure   En   Endpoints compatible   Instruct   Quantized   Qwen2   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit 

Qwen2.5 0.5B Instruct Bnb 4bit Parameters and Internals

Model Type 
Causal Language Models
Additional Notes 
Significant improvements in knowledge, coding, mathematics, and instruction following abilities. Multilingual support for more than 29 languages. Long-context support up to 128K tokens, generating up to 8K tokens. Robust against diverse system prompts, enhancing chatbot capabilities.
Supported Languages 
English (Fluent), Chinese (Fluent), French (Fluent), Spanish (Fluent), Portuguese (Fluent), German (Fluent), Italian (Fluent), Russian (Fluent), Japanese (Fluent), Korean (Fluent), Vietnamese (Fluent), Thai (Fluent), Arabic (Fluent)
Training Details 
Context Length:
32768
Model Architecture:
Transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
Input Output 
Input Format:
Structured input using predefined roles in JSON format
Accepted Modalities:
text
Output Format:
JSON
LLM NameQwen2.5 0.5B Instruct Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit 
Base Model(s)  Qwen/Qwen2.5-0.5B-Instruct   Qwen/Qwen2.5-0.5B-Instruct
Model Size0.5b
Required VRAM0.5 GB
Updated2026-08-08
Maintainerunsloth
Model Typeqwen2
Instruction-BasedYes
Model Files  0.5 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.49.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen2.5 0.5B Instruct Bnb 4bit

Model
Likes
Downloads
VRAM
Omega Attention 0.5B0430 GB
Pgabl Ft Nama Siswa02531 GB
Legal Rag Qwen Sft02041 GB
...mmanuel Siagian Exp1 Lr2e5 R160111 GB
BoyBarley Sparky0171 GB

Best Alternatives to Qwen2.5 0.5B Instruct Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Pgabl Ft Nama Siswa32K / 1 GB2530
Legal Rag Qwen Sft32K / 1 GB2040
Atomight V2.2 UltraThink 0.5B32K / 1 GB541
...mmanuel Siagian Exp1 Lr2e5 R1632K / 1 GB110
BoyBarley Sparky32K / 1 GB170
...0.5B Instruct Unsloth Bnb 4bit32K / 0.5 GB353606
Qwen2.5 0.5B Instruct 4bit32K / 0.3 GB157697
...5 Coder 0.5B Instruct Bnb 4bit32K / 0.5 GB66124
TinySphinx32K / 1 GB340
... Instruct Unsloth Merged 16bit32K / 1.3 GB252
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit.