Unverified50% confidenceBenchmarkExact time
Under Q2K quantization, average generation speed is 13.9 tokens per second for short texts, 10.5 for long texts, and peaks at approximately 18.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedThe Q2_K quantized model's accuracy doubled from 12% to 24%.73% similarUnverifiedIQ2_XXS以约2.06位的平均比特率对权重编码，相比IQ3_S（约3.44位）或Q4_K_M（约4.83位）压缩率更高但信息损失更大63% similarUnverified对于Lorenz系统，最大Lyapunov指数约为0.9，意味着初始误差每经过约1.1个时间单位就翻倍61% similarUnverifiedQ2_K quantization compresses model weights to an average of approximately 2.5 bits, reducing VRAM usage to roughly one-sixth of the original, but causes significant degradation of model capability, jokingly referred to in the industry as a lobotomy.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978659API
curl https://kongchang.com/api/v1/knowledge/claims/978659MCP
get_claim(id=978659)