Unsloth AI ✓

@UnslothAI · San Francisco, CA · joined 30 Nov 2023

Run and train models locally with the Unsloth Desktop app. 🦥 https://t.co/2kXqhhvdCD

96 557Followers

478Following

768Posts total

12.4MViews on collected posts

Against accounts of the same size

8 posts from the last 90 days, next to the 10K–100K follower range. shown widely, but few of those viewers react.

Median views960 606this account3 137median for 10K–100K

Reach, %994.86%this account10.26%median for 10K–100K

Engagement, %0.69%this account1.47%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	960 606	3 137	306×
Reach (views ÷ followers)	9.9× audience	10.26%	97.0×
Engagement rate	0.69%	1.47%	0.47×

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

804.2K11 Aug

1.8M26 Aug

6.6M

1.1M

302.9K27 Aug

1.4M28 Aug

224.1K

100.3K2 Sep

Last 8 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.73%11 Aug

0.54%26 Aug

0.44%

0.28%

0.67%27 Aug

0.71%28 Aug

1.01%

1.31%2 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.47%.

What the audience does

Likes67.0%52 157 in total

Reposts7.9%6 112 in total

Replies3.1%2 373 in total

Quotes4.2%3 240 in total

Bookmarks17.9%13 911 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

Qwen3.8-Flash can now run 1.7× faster locally with MTP!⚡️ GGUFs can reach 170 tokens/s on a RTX PRO 6000. MTP enables Qwen3.8-Flash-Next ~1.3–1.7× faster inference with no accuracy change. GGUFs: https://t.co/vXkjO3W0fj Guide: https://t.co/LLMclyJTeL https://t.co/KuWfuLOJBR 100.3K views · 1.1K likes · 124 reposts · 60 replies 02 Sep 2026 GLM-5.3 can now be run locally! The 2-bit model retains ~81% accuracy after we shrunk it from 1.51TB to 239GB (-83% size). Run on a 256GB Mac or RAM/VRAM setups. GLM-5.3 is the strongest open model to date. Guide: https://t.co/NLgb3CMB6A GGUF: https://t.co/Sqwq3xjgo5 https:// 224.1K views · 1.9K likes · 213 reposts · 100 replies 28 Aug 2026 GLM-5.3 is now open-weight. Our most capable model for agentic coding and cyber defense is now available to download, run, and customize. Weights: https://t.co/v1IbWMXxg4 Tech blog: https://t.co/ekQkO83jCv https://t.co/f8XlJksKyf 1.4M views · 8.5K likes · 954 reposts · 273 replies 28 Aug 2026 GLM-5.3-Flash can now be run locally! ✨ Run 3-bit on 128GB RAM via Unsloth GGUF. GLM-5.3-Flash (ox-alpha) rivals Claude Opus 4.8 on DeepSWE, coding & agentic benchmarks. Guide: https://t.co/oItBKYNrl9 GGUF: https://t.co/E73FKC7IKM https://t.co/V1t8fDIUtp 302.9K views · 1.7K likes · 201 reposts · 106 replies 27 Aug 2026 Qwen3.8-Flash can now be run locally! 🔥 The 125B MoE model outperforms Claude-Opus-4.6 (Max). Run on 75GB RAM via Unsloth GGUFs. Qwen3.8-Flash-Next enables CPU RAM / unified mem setups to deliver near VRAM speeds. Guide: https://t.co/LLMclyJTeL GGUF: https://t.co/vXkjO3W0fj h 1.1M views · 2.5K likes · 318 reposts · 164 replies 26 Aug 2026 Introducing GLM-5.3-Flash - Leading capabilities at a highly competitive price - Natively multimodal with a 1M-token context window - A 320B-A18B model released under the MIT License - Previously previewed as Ox Alpha, running entirely on Chinese AI chips Blog: https://t.co/KOC 6.6M views · 23.8K likes · 2.6K reposts · 979 replies 26 Aug 2026 ⚡Meet Qwen3.8-Flash, a multimodal MoE and an early preview of the Qwen4 architecture, now open-weight! The production version Qwen3.8-Flash will be available soon via QwenCloud API at just $ 0.16/1M input tokens and $ 0.47/1M output tokens. 125B parameters + 51B N-gram https:// 1.8M views · 7.8K likes · 1K reposts · 419 replies 26 Aug 2026 Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windows and Linux • Supports MLX, diffusion image/video, audio, GGUF • Connect Claude Code and Codex to local LLMs • 50% more accurate, self-healing tool calls + http 804.2K views · 4.8K likes · 634 reposts · 272 replies 11 Aug 2026