LLM EXPLORER 66,845 MODELS INDEXED

AHN DN For Qwen 2.5 Instruct 3B by ByteDance-Seed

By ByteDance-Seed · 125 downloads

AHN DN For Qwen 2.5 Instruct 3B is an open-source language model by ByteDance-Seed. Features: 3b LLM, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.2.

  Arxiv:2510.07318 Base model:finetune:qwen/qwen2...   Base model:qwen/qwen2.5-3b   Chat   En   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors

AHN DN For Qwen 2.5 Instruct 3B Parameters and Internals

LLM NameAHN DN For Qwen 2.5 Instruct 3B
Repository πŸ€—https://huggingface.co/ByteDance-Seed/AHN-DN-for-Qwen-2.5-Instruct-3B 
Base Model(s)  Qwen/Qwen2.5-3B   Qwen/Qwen2.5-3B
Model Size3b
Required VRAM0 GB
Updated2026-10-21
MaintainerByteDance-Seed
Model Typeqwen2
Instruction-BasedYes
Model Files  0.0 GB
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.49.0
Vocabulary Size151936
Torch Data Typebfloat16

Best Alternatives to AHN DN For Qwen 2.5 Instruct 3B

Best Alternatives
Context / RAM
Downloads
Likes
VibeThinker 3B128K / 6.2 GB52745806
VibeThinker 3B128K / 6.2 GB3610
Saba2 3B128K / 6.2 GB60
Tessa T1 3B117K / 6.2 GB105
UIGEN T1.5 3B117K / 6.2 GB71
Qwen2.5 3B Instruct32K / 6.2 GB5889234545
Swarmhunter 3B32K / 6.2 GB3211
SmallThinker 3B Preview32K / 6.8 GB30529412
... Instruct Sheldon RLVR Math V132K / 6.2 GB8760
Zen Ingress 1 3B Sft Merged32K / 6.2 GB8341
Note: green Score (e.g. "73.2") means that the model is better than ByteDance-Seed/AHN-DN-for-Qwen-2.5-Instruct-3B.