Unverified50% confidenceOpinionExact time
The activation ratio of Inkling 2 Small is about one-thirtieth of the total parameters (17B/594B), indicating that Thinking Machines has done fairly aggressive sparsification in expert routing.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/6/2026
First Seen
Valid until: 2/4/2027
Sources
Related Entities
Related Claims
UnverifiedIncorporating an encoder into the architecture yields a rough estimated inference speed improvement of approximately 25%, as the amount of computation is reduced by roughly one quarter.69% similarUnverifiedIn 10%–25% of cases, reasoning about the hypothetical grader pulled the agent's work away from the user's original specification.68% similarUnverifiedThe smallest version of MiniMind has approximately 26 million to 64 million parameters.68% similarUnverifiedThe lower the quantization bit depth, the more likely the model is to show degraded performance on detailed reasoning, but for most tasks at quantization levels above 4-bit, the experiential difference is not obvious to ordinary users.68% similarVerifiedThe Mixture of Experts (MoE) architecture activates only approximately 10%–30% of total parameters during inference, significantly reducing FLOPs and GPU memory usage per inference67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1142576API
curl https://kongchang.com/api/v1/knowledge/claims/1142576MCP
get_claim(id=1142576)