dots.llm1 Instruct

Overview

Xiaohongshu's first LLM under the Rednote brand — a 142B MoE with 14B active params trained without synthetic data, matching Qwen2.5-72B. Released under MIT.

When to pick this model

• Creative and lifestyle content generation
• Chinese-language social and consumer-facing products
• Research on training without synthetic data
• MIT-licensed alternative to Qwen for content-heavy use cases
• Workloads where natural, non-generic prose matters

VRAM requirements by quantization

Quantization	VRAM required
Q4_K_M (recommended)	85 GB
Q5_K_M	102 GB
Q8_0	152 GB
FP16 (no quantization)	284 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Strengths

• 14B active params in a 142B MoE — efficient inference
• MIT license
• Strong creative and lifestyle content generation
• No synthetic data in training — more natural outputs

Limitations

• Roughly 85 GB VRAM in Q4 — multi-GPU territory
• 32k context lags modern flagships
• Output style optimized for Chinese social media — may not fit Western tone

Architecture & training

Architecture: MoE · 142B total / 14B active · Rednote (Xiaohongshu) · 32k ctx

Training: Rednote — strong in creative generation and lifestyle content.

Quick start

ollama pull hf.co/rednote/dots-llm1-GGUF

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.