GreenBitAI/LLaMA-2-1.1B-2bit-groupsize32
Text Generation • Updated • 14 • 4
Haojin Yang
yanghaojin
AI & ML interests
None yet
Recent Activity
published a model about 2 months ago
GreenBitAI/Qwen3.5-27B-layer-mix-bpw-4.5-mlx reacted to theirpost with 🚀 8 months ago
Our new blog post Smaller Models, Smarter Agents 🚀 https://huggingface.co/blog/yanghaojin/greenbit-3-bit-stronger-reasoning
DeepSeek’s R1-0528 proved that 8B can reason like 235B. Anthropic showed that multi-agent systems boost performance by 90%. The challenge? Both approaches burn massive compute and tokens.
💡 GreenBitAI cracked the code:
We launched the first 3-bit deployable reasoning model — DeepSeek-R1-0528-Qwen3-8B (3.2-bit).
✅ Runs complex multi-agent research tasks (e.g. Pop Mart market analysis)
✅ Executes flawlessly on an Apple M3 laptop in under 5 minutes
✅ 1351 tokens/s prefill, 105 tokens/s decode
✅ Near-FP16 reasoning quality with just 30–40% token usage
This is how extreme compression meets collaborative intelligence — making advanced reasoning practical on edge devices. posted an update 8 months ago
I’m excited to share this article https://huggingface.co/blog/yanghaojin/greenbitais-4-bit-models-redefine-ai-efficiency, showcasing the power of low-bit small models in programming tasks. 🚀 Stay tuned—the next post will dive into test cases for small model–driven agentic applications!Organizations
liked 2
models over 2 years ago
liked a
Space over 2 years ago
liked 4
models over 2 years ago
liked 2
models almost 3 years ago