Unverified50% confidenceBenchmarkExact time
System 1 models with 4B parameters or more have a weighted ECE under syntactic perturbation (ECE_w) of 0.030 to 0.087, versus 0.144 for the log-probability baseline and 0.378 for the JSON-decoding baseline.
1
Sources
50%
Confidence
Long-term
Relevance
11/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn speculative decoding, the draft model's parameter count is typically about 1/10 to 1/5 of the target model, and the candidate count k is typically 4-8.66% similarUnverifiedLarge language models that can run on-device typically have parameter scales of 1B to 13B, far smaller than cloud-based models such as GPT-4 or Claude with hundreds of billions of parameters.65% similarUnverified对于7B至13B参数级别的模型,4-bit量化后的输出质量与全精度版本差异很小64% similarUnverifiedThe same Gemma 4 E2B model varies from 34.9 to 131.9 tokens/s in single-request generation speed across different AWS inference backends, a significant gap.64% similarUnverified4B表示模型参数量为40亿,属于小型语言模型(SLM)范畴64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1155168API
curl https://kongchang.com/api/v1/knowledge/claims/1155168MCP
get_claim(id=1155168)