Unverified50% confidenceFactExact time
The largest 209M-parameter version in the Timestral family can run inference on CPU.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedMistral launched Timestral, its first time-series foundation model family, with four sizes (5M, 28M, 123M, and 209M), running purely on CPU, with per-forecast latency of 10–140ms and support for a 32768-step context.78% similarUnverifiedA 1.5-millisecond CPU inference means the detection module can be embedded into existing inference pipelines without additional GPU resources.67% similarUnverified实测项目使用的芯片型号为STM32F103C8T6，系统时钟配置为72MHz，GPIO配置在PC13引脚66% similarUnverified现代多核CPU上，根据模型大小和量化不同，纯CPU推理大约能跑到每秒5到20个token。65% similarUnverifiedTechnical approaches for achieving efficient TTS inference include ONNX Runtime or TensorRT acceleration, KV-Cache to reduce redundant computation, INT8/FP16 quantization, and Speculative Decoding.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1065231API
curl https://kongchang.com/api/v1/knowledge/claims/1065231MCP
get_claim(id=1065231)