Unverified50% confidenceFactExact time
Thinking Machines, founded by former OpenAI CTO Meera Muradi, built its first model Inkling mainly on the DeepSeek V3 architecture.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/10/2026
First Seen
Valid until: 2/8/2027
Sources
Related Entities
Related Claims
UnverifiedThinking Machines released the Dimuon optimizer, a Muon variant designed specifically for LoRA fine-tuning, and it has been released in Tinker.69% similarUnverifiedThe working solution relies on a combination: DeepSeek provides the weights, coolbho3k does the 3-bit quantization, turboderp wrote the EXL3 format and the ExLlamaV3 inference library, Victor Cruz wrote the vllm-exl3 bridge layer, Diffbot designed the per-expert split scheme, startup flow and kernels, and InferenceKey did the integration and measurement.63% similarUnverified常见的推理引擎包括NVIDIA的TensorRT、微软的ONNX Runtime、Intel的OpenVINO63% similarUnverifiedDeepSeek V3和R1采用MoE(混合专家)架构,使Mac Studio或DGX Spark这类设备能以可用速度运行大模型62% similarUnverifiedInference acceleration tools include TensorRT, ONNX Runtime, OpenVINO, and others, used for graph optimization and hardware adaptation of models.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1154990API
curl https://kongchang.com/api/v1/knowledge/claims/1154990MCP
get_claim(id=1154990)