LLM EXPLORER 55,709 MODELS INDEXED

Marco DeepResearch 8B by AIDC-AI

By AIDC-AI · 520 downloads
HF Repo ↗ Copy URL

Marco DeepResearch 8B is an open-source language model by AIDC-AI. Features: 8b LLM, VRAM: 16.3GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.27.

  Arxiv:2603.28376   Agent Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-8b   Conversational   Deep-research   En   Endpoints compatible   Information-seeking   Model-index   Qwen3   React   Region:us   Safetensors   Sharded   Tensorflow   Verification   Web-search   Zh
Model Card on HF 🤗: https://huggingface.co/AIDC-AI/Marco-DeepResearch-8B 

Marco DeepResearch 8B Parameters and Internals

LLM NameMarco DeepResearch 8B
Repository 🤗https://huggingface.co/AIDC-AI/Marco-DeepResearch-8B 
Base Model(s)  Qwen3 8B   Qwen/Qwen3-8B
Model Size8b
Required VRAM16.3 GB
Updated2026-05-26
MaintainerAIDC-AI
Model Typeqwen3
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.4 GB: 4-of-4
Supported Languagesen zh
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.57.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Marco DeepResearch 8B

Best Alternatives
Context / RAM
Downloads
Likes
...n3 8B 320K Context 10X Massive320K / 16.4 GB200
...r Of Horror Jan V1 256K Ctx 8B256K / 16.1 GB333
... BIG Jan Horror V1 256K Ctx 8B256K / 16.1 GB440
Qwen3 8B 256K Context 8X Grand256K / 16.4 GB950
...wen3 8B 192K Context 6X Larger192K / 16.4 GB550
DeepSeek R1 0528 Qwen3 8B128K / 16.4 GB17622931082
Marco DeepResearch 8B128K / 16.3 GB24234
Finch 8B128K / 16.4 GB923
BehChat SFTv3 Ckpt3128K / 16.4 GB870
BehChat V2.1128K / 16.4 GB130
Note: green Score (e.g. "73.2") means that the model is better than AIDC-AI/Marco-DeepResearch-8B.