Reply points to the full Thinky model card after SGLang and vLLM support landed
TheZachMueller · x · 2026-07-22
A reply that points to the full Thinky model card.
It adds no new facts beyond the benchmark post: the card was published after SGLang and vLLM support were in place, and the model is positioned as fast and capable.
Related event: Thinky Releases Model Card with B200 Benchmark Data(2 posts)→
More from Models
- Testing LLMs with a Churchill Insult Prompt: GPT Outperforms Kimi and Gemini — emollick · 2026-07-23
- NVIDIA Recaps Kaggle Nemotron Challenge: 5,000+ Explore Open Model Reasoning — NVIDIAAI · 2026-07-23
- Kimi K3 Sets New Open-Weights Record on Epoch Capabilities Index, Approaching GPT-5 — rohanpaul_ai · 2026-07-23
- GLM 5.2 Reportedly Handles Multi-Node H100 Clusters, Emerging as Top Open-Weights Autoresearch Model — _ScottCondron · 2026-07-23
- Qwen3.6 35B multimodal GGUF build starts trending on Hugging Face — LuffyTheFox · 2026-07-23
- Post says the U.S. led open models first, then let closed models take over — cocktailpeanut · 2026-07-23