SparkLLM ✓

@SparkLLM

Leading general-purpose foundation models & professional AI agents. The proprietary Spark model family, with AStudio & Loomy harnesses. Open source.

924Followers

17Following

19Posts total

122.1KViews on collected posts

Against accounts of the same size

6 posts from the last 90 days, next to the under 10K follower range. ordinary reach for its size, weaker reaction than most.

Median views4 257this account6 244median for under 10K

Reach, %460.71%this account415.20%median for under 10K

Engagement, %0.71%this account1.06%median for under 10K

Metric	This account	Median for under 10K	Ratio
Median views per post	4 257	6 244	0.68×
Reach (views ÷ followers)	4.6× audience	4.2× audience	1.11×
Engagement rate	0.71%	1.06%	0.67×

Others in this range → Compare with another account → How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

4.1K1 Sep

4.8K

103.8K

3.1K

4.4K

1.9K

Last 6 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.59%1 Sep

0.83%

0.64%

0.78%

1.49%

0.37%

Reactions — likes, reposts, replies and quotes — divided by views. Median for under 10K accounts is 1.06%.

What the audience does

Likes53.9%706 in total

Reposts5.2%68 in total

Replies2.3%30 in total

Quotes1.5%19 in total

Bookmarks37.1%486 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Latest posts

@SparkLLM 1M 上下文塞进 1.7B，这数字本身就有股「先报再跑」的味道。谁先贴个 800k needle，谁才算交差 👀 1.9K views · 7 likes · 0 reposts · 0 replies 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 4.4K views · 59 likes · 5 reposts · 1 replies 01 Sep 2026 API is live on iFlytek Xingchen MaaS (free for a limited time): https://t.co/fC7kZlDOdk Next up — on Sep 7, Spark X2.5-293B with upgraded code & agent capabilities. #opensource #edgeAI #LLM 3.1K views · 21 likes · 1 reposts · 1 replies 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. 🧵👇 103.8K views · 559 likes · 60 reposts · 26 replies 01 Sep 2026 Why 1M context on-device? So the model can read a whole product manual, a full codebase, or a batch of docs in one pass — and keep the full picture across a multi-step task, all locally. No more chopping documents into fragments. 4.8K views · 38 likes · 1 reposts · 1 replies 01 Sep 2026 It doesn't just read — it does the work. On the Domux smart-home test set, X2.5-1.7B reaches 90.3% end-to-end command accuracy at 0.85s average latency. On coding, the 4B rivals cloud models 2–3× its size. 4.1K views · 22 likes · 1 reposts · 1 replies 01 Sep 2026