Unverified50% confidenceBenchmarkExact time
On the two benchmarks AppWorld and τ³, tested with two target models, SpecCompact achieved compression speedups of 2.04 to 5.63 times compared with Hermes-style summarization.
1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn a model comparison test, qwen2.5:3b correctly understood pace, produced 0 hallucinated place names, had a length error of 0.3%, peak memory of 259 MB, and took 106 seconds.64% similarUnverified在27B混合架构、4B稠密模型、36B MoE三类模型上以8k上下文测试，Prefill阶段性能无变化，Decode阶段打补丁后快约1.4%63% similarUnverifiedIn the B300 EP8 decoding scenario, Chord achieves a 2.15× speedup compared to the untuned default implementation.62% similarUnverifiedThe performance gap between a carefully quantized 4-bit model and the original FP16 model is typically within 1–3 percentage points.61% similarUnverifiedAfter restoring flushing, the Claude candidate achieved a completion speedup of 2.75× and a time-to-first-byte speedup of 2.80×, while Gemini achieved a completion speedup of 3.44× and a time-to-first-byte speedup of 3.54×, and GPT-5.4 achieved a completion speedup of 2.16× and a time-to-first-byte speedup of 2.19×.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1139051API
curl https://kongchang.com/api/v1/knowledge/claims/1139051MCP
get_claim(id=1139051)