[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
@alexchen4ai Alex Chen-Nexa AI
Alex Chen-Nexa AI posts on X about the worlds, breakthrough, gpu, $2454tw the most. They currently have XXX followers and XX posts still getting attention that total XXX engagements in the last XX hours.
Engagements: XXX #
- X Week XXXXX +1,221%
- X Month XXXXX -XXXX%
- X Months XXXXX +502%
- X Year XXXXX +126%
Mentions: X #
- X Week X +167%
- X Month XX -XX%
- X Months XX +640%
- X Year XX +270%
Followers: XXX #
- X Week XXX -XXXX%
- X Month XXX +1.50%
- X Months XXX -XX%
- X Year XXX +428%
CreatorRank: XXXXXXXXX #
Social Influence #
Social category influence stocks technology brands
Social topic influence the worlds, breakthrough, gpu, $2454tw #147, scratch, stack, team and
Top Social Posts #
Top posts by engagements in the last XX hours
"RAG mattersand its usually X models: embeddings rerank and an LLM. Today were running all three fully on the @Qualcomm NPU with SOTA models: - Embedding: @GoogleDeepMind EmbeddingGemma-300M - Rerank: @JinaAI_ Reranker v2 - Generate: @IBMResearch Granite 4.0-Micro Why it matters - XX less power truly always-on - On-device & XXX% private your data stays local - Cooler + quieter better user experience We also open-sourced a demo project for Snapdragon AI PC developers: 🔗 Together full-stack SOTA retrieval + generation on NPU. #OnDeviceAI #RAG #NPU #Snapdragon #Qualcomm #EdgeAI #PrivateAI"
X Link @alexchen4ai 2025-10-13T16:26Z XXX followers, XXX engagements
"Excited about the starting point of the Qwen3VL support. And it is just the starting point We will soon have comprehensive support for more upcoming Qwen3VL support"
X Link @alexchen4ai 2025-10-04T19:55Z XXX followers, XXX engagements
"Nexa AI brings Day-0 full-platform inference for Qwen3-VL-4/8Bacross NPU GPU and CPU on Apple Qualcomm AMD Intel MediaTek and NVIDIA. We built the core engine NexaML from scratch and deeply optimized GGML and MLX delivering a truly Unified Inference Engine tuned for every hardware stack. With close collaboration with the Qwen team and leading silicon partners multimodal understanding and vision reasoning now run locallycombining performance and privacy. No waiting no portingone command and youre live on every device. The future of multimodal AI isnt in the cloudits in your hands"
X Link @alexchen4ai 2025-10-14T17:30Z XXX followers, 1539 engagements
"@_JoshuaTimothy @nexa_ai @Alibaba_Qwen @Apple @Qualcomm @nvidia @intel @MediaTek @AMD Hi Joshua can you pull the model and try it again We improved the quantization quality yesterday"
X Link @alexchen4ai 2025-10-16T18:52Z XXX followers, XX engagements
"@_JoshuaTimothy @nexa_ai @Alibaba_Qwen @Apple @Qualcomm @nvidia @intel @MediaTek @AMD Thanks working on it now This is really helpful"
X Link @alexchen4ai 2025-10-16T23:06Z XXX followers, XX engagements
"@sir4K_zen @nexa_ai @Alibaba_Qwen @Apple @Qualcomm @nvidia @intel @MediaTek @AMD Yes this is in the pipeline"
X Link @alexchen4ai 2025-10-15T20:00Z XXX followers, XX engagements
"@Alibaba_Qwen @nexa_ai Appreciate the partnership"
X Link @alexchen4ai 2025-10-14T17:43Z XXX followers, XX engagements