Summary
According to a post on X by @parthsareen, Thinking Machines has released the full Inkling 2 Small checkpoint on Hugging Face under the Apache 2.0 license, a week after launching it as hosted-only. The post describes it as a 594B-parameter mixture-of-experts model with 17B active parameters and image input. The company's blog reportedly lists support for SGLang, vLLM and Unsloth, plus API access through NVIDIA, Fireworks, Together, Cloudflare and others. The post also says list members shared that the model is landing on Ollama and Cloudflare Workers AI.
AI-assisted summary based on the listed source.
What happened
Thinking Machines released the full Inkling 2 Small checkpoint on Hugging Face under Apache 2.0, a week after the hosted-only launch; it is a 594B-parameter mixture-of-experts model with 17B active parameters and image input. Its blog lists SGLang, vLLM and Unsloth support and API access via NVIDIA, Fireworks,...
Why it matters
Developers who want to run or fine-tune the model themselves can now download the weights rather than relying only on a hosted API. Teams using hosted inference can compare the providers named in the post. Watch whether Ollama and Cloudflare Workers AI confirm their listings, since the post only says these were shared by list members.
What this means for you
Hardware and robotics watchers may want to track whether this becomes a product, benchmark, or deployment signal.
Signal Intelligence
Signal Strength 95%
Technical label WATCH
Public Interest 63
Category ROBOTS & HARDWARE
Reader Depth TECHNICAL
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
Recognizable Entity Score 68
Practical Impact Score 64
Novelty Interest Score 94
Consequence Score 34
Curiosity Score 16
Shareability Score 72
Why this is here
VQV surfaced this signal because it is recent, relevant to Open Source LLMs, connected to Scobleizer News Pulse (X).
