LLMYourWay
ModelsDevices
Edge AI
CompareInsights
Enterprise

flashresearch

1 models • 1 total models in database
Sort by:

FlashResearch-4B-Thinking

[](https://huggingface.co/your-username/your-model-name) [](#license) [](https://huggingface.co/datasets/cheapresearch/CheapResearch-DS-33k) A 4B-parameter Qwen model distilled from Tongyi DeepResearch-30B A3B, optimized for web-scale “deep research” tasks and inference with Alibaba-NLP/DeepResearch. Base: Qwen 4B (dense) Teacher: Tongyi DeepResearch 30B A3B (MoE) Method: SFT distillation on 33k curated deep-research examples Dataset: `flashresearch/FlashResearch-DS-33k` Primary Use: Fast, low-cost DeepResearch agent runs (browsing, multi-step reasoning, source-grounded answers) Primary dataset: `flashresearch/FlashResearch-DS-33k` Inference with Alibaba-NLP/DeepResearch (Recommended) This model is intended to be used directly with the DeepResearch repo. Single 12–16GB GPU is enough for 4B FP16; FP8/INT4 quantization allows smaller VRAM. If you quantize, the summary model can be local as well. Qwen team for the base 4B architecture Alibaba-NLP for DeepResearch CheapResearch contributors for the 33k dataset v1.0.0 (2025-10-04) — First public release (33k distillation, DeepResearch-ready)

NaNK
license:mit
94
19
LLMYourWay

The definitive AI model comparison platform. Compare 12K+ models, track performance, and discover the perfect AI solution for your needs.

Made with AI
Real-time Data

Product

  • Find Your Device
  • Browse Models
  • Compare AI
  • Benchmarks
  • Pricing
  • API Access

Resources

  • Blog & Articles
  • Methodology
  • Changelog
  • Trending
  • Use Cases

Company

  • About
  • Contact

Legal

  • Privacy Policy
  • Cookie Policy
  • Terms of Service
12K+12,000+
AI Models Tracked & Updated Daily
© 2026 LLMYourWay. All rights reserved.
Data updated every 4 hours
Powered by real-time AI data
API