vLLM @vllm_project · 01 Sep 2026
🚀 SparkLLM open-sources Spark X2.5-4B & X2.5-1.7B — the only on-device models with native context up to 1,000,000 tokens. Hybrid-attention architecture, tuned for agents, code, math & instruction following. 🧵👇
101 358Views
556Likes
60Reposts
25Replies
17Quotes
0Bookmarks
Is that a lot?
3.90×vs this author's median25 968 views is typical
83Percentile for this authorof 6 recent posts
36.8×vs 10K–100K median2 751 views is typical
2.1× audienceReachviews ÷ followers
0.65%Engagement rateof viewers reacted