LLM EXPLORER 61,249 MODELS INDEXED

Diraya 3B Instruct Ar by Omartificial-Intelligence-Space

Diraya 3B Instruct Ar is an open-source language model by Omartificial-Intelligence-Space. Features: 3b LLM, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.17.

  Arxiv:2407.10671   4bit   Ar   Arabic   Conversational   Dira   Instruct   Lora   Peft   Quantized   Qwen   Reasoning   Region:us   Safetensors   Unsloth

Diraya 3B Instruct Ar Parameters and Internals

LLM NameDiraya 3B Instruct Ar
Repository πŸ€—https://huggingface.co/Omartificial-Intelligence-Space/Diraya-3B-Instruct-Ar 
Base Model(s)  unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit   unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit
Model Size3b
Required VRAM0 GB
Updated2026-08-04
MaintainerOmartificial-Intelligence-Space
Instruction-BasedYes
Model Files  0.5 GB   0.2 GB   0.0 GB   0.0 GB
Supported Languagesar
Quantization Type4bit
Model ArchitectureAutoModel
Licenseapache-2.0
Model Max Length32768
Is Biasednone
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesk_proj|gate_proj|o_proj|down_proj|v_proj|up_proj|q_proj
LoRA Alpha64
LoRA Dropout0
R Param64
Errorsreplace

Best Alternatives to Diraya 3B Instruct Ar

Best Alternatives
Context / RAM
Downloads
Likes
PSC0K / 0.1 GB50
Sage Assistant Lora0K / 0.1 GB210
Qwen2.5 Coder 3B Unsloth Lora0K / 0.1 GB71
Qwen 2.5 3B R1 Lora Model V.10K / 0.1 GB01
Llama 3.2 3B R1 Lora0K / 0.1 GB02
Llama 3.2 3B Smart V1 Lora0K / 0.1 GB01
...lama 3.2 3B General Lora Model0K / 0.1 GB01
Llama 3.2 3B Code Lora Model0K / 0.1 GB02
Qwen 2.5 3B Rp Lora Model0K / 0.1 GB03
Llama 3.2 3B Lora Model0K / 0.1 GB04
Note: green Score (e.g. "73.2") means that the model is better than Omartificial-Intelligence-Space/Diraya-3B-Instruct-Ar.