Unverified50% confidenceBenchmarkExact time
On 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).
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/19/2026
First Seen
Valid until: 11/2/2026
Sources
Related Entities
Related Claims
UnverifiedIn a Qwen model decoding scenario at depth 512, SonicBoom's performance is only 0.98 times that of llama.cpp.69% similarUnverifiedd1-omni-600M 包含 381M 共享主干加决策头、94M SigLIP2 视觉编码器（来自 LFM2.5-VL-450M）和 112M 17 层 FastConformer 音频编码器。68% similarUnverifiedThe experimental environment is built around a single NVIDIA RTX 3090 (24 GB VRAM, 390 W power limit), on which two shared services run: a Whisper ASR transcription service and nomic-embed-text (Ollama).68% similarUnverifiedA Bilibili uploader used llama.cpp to load the 1-bit quantized version of GLM 5.3 Flash on 4 RTX 3090s, achieving a generation speed of 33.5 tok/s.67% similarUnverifiedRTX 4090搭载的GDDR6X显存由美光（Micron）开发，采用PAM4信号编码，带宽超过1000 GB/s（1008 GB/s）67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067199API
curl https://kongchang.com/api/v1/knowledge/claims/1067199MCP
get_claim(id=1067199)