SparkLLM @SparkLLM · 01 Sep 2026
Trained on ~20T tokens on fully domestic compute. Runs on NVIDIA / Huawei / Hygon; vLLM, SGLang, llama.cpp; Ollama & LM Studio; fine-tune with LLaMA-Factory. Weights & code: https://t.co/x9AlVyYoys 🤗 https://t.co/D2iMd5gPXe
4 420Views
59Likes
5Reposts
1Replies
1Quotes
56Bookmarks
Is that a lot?
1.04×vs this author's median4 257 views is typical
50Percentile for this authorof 6 recent posts
0.71×vs under 10K median6 244 views is typical
4.8× audienceReachviews ÷ followers
1.49%Engagement rateof viewers reacted