Unverified50% confidenceFactExact time
The numbers in Strata's speed table are all self-tested by the developer and have not been independently verified; figures for other GPUs (such as the 5060 Ti and 3090) are estimates with a ±20% margin of error.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedIn Strata's speed table, under a 128k context, Q2_0 (2-bit) achieves 65.1 tokens/s and IQ2_XS achieves 52 tokens/s; under a 4k short context, IQ3_XXS achieves 65.6 tokens/s.64% similarUnverifiedStrata automatically recommends quantization tiers based on memory: Q2 for 37.6 GB, iQ2XS (officially recommended) for close to 40 GB, higher tiers for 64 GB and above, and a Coder IQ1 version for coding scenarios.64% similarUnverifiedClaude Opus 4.6 produced 30 times more errors than GPT-5.4, averaging 2.5 errors per trajectory vs. 0.08, with the difference being statistically significant (p < 0.0001, Cliff's δ = 0.613).63% similarUnverifiedAS5048 数据手册中标注的实际精度（考虑积分非线性误差 INL）通常在 ±0.5 度左右62% similarUnverifiedThe best-performing Edu-QuRater achieved an average accuracy of 0.917 in reproducing GPT-4.1-mini pairwise judgments on the held-out set.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978811API
curl https://kongchang.com/api/v1/knowledge/claims/978811MCP
get_claim(id=978811)