Unverified50% confidenceBenchmarkExact time
In a Qwen model decoding scenario at depth 512, SonicBoom's performance is only 0.98 times that of llama.cpp.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/19/2026
First Seen
Valid until: 11/2/2026
Sources
Related Entities
Related Claims
UnverifiedOn a desktop-class RTX 3050 8GB graphics card, using the same GGUF model and the same session, SonicBoom v0.0.3 achieved better performance in the decoding phase than llama.cpp (-ngl 99).69% similarUnverifiedQwen2 0.5B模型（5亿参数）运行仅需约352MB显存68% similarUnverifiedOn the Qwen 3.8 Flash Next model, decoding performance doubled to 52 tok/s.68% similarUnverifiedThe Q4_K_M/GGUF version of Qwen 27B decodes at approximately 10.7 tok/s on the same machine, roughly 1/3.8 of the MLX version.68% similarVerifiedQwen3 27B scored 90.3 on LiveCodeBench V6, slightly surpassing Opus 4.6 Max's score of 88.8.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067204API
curl https://kongchang.com/api/v1/knowledge/claims/1067204MCP
get_claim(id=1067204)