Unverified50% confidenceBenchmarkExact time
On three benchmarks with Qwen3-8B as the target model, D3D still retains over 99% of the average acceptance length after pruning 5 of 36 layers.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/5/2026
First Seen
Valid until: 2/3/2027
Sources
Related Entities
Related Claims
UnverifiedIn evaluations across seven benchmarks, D3D achieves an average decoding speedup of 5.00x with Qwen3-8B as the target model.75% similarUnverifiedQwen3.8-Flash-Next has a 48-layer structure with 512 experts per layer and 180B-class parameters (125B main body + 51B N-gram table + 4B MTP).66% similarUnverifiedUnder the same settings, DFlash achieves average decoding speedups of 4.03x and 3.67x with Qwen3-8B and Qwen3-32B as target models, respectively.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1137901API
curl https://kongchang.com/api/v1/knowledge/claims/1137901MCP
get_claim(id=1137901)