BUFU's submissions | Hacker News

1.		We Ran GPT‑OSS 20B Local on a Phone (nexa.ai)
		1 point by BUFU 5 months ago \| past
2.		Qwen3-VL-30B-A3B-Instruct and Thinking (huggingface.co)
		6 points by BUFU 6 months ago \| past
3.		New Engine to Run SOTA AI Models on Qualcomm NPU Across Phone, PC, Cars, and IoT (nexa.ai)
		1 point by BUFU 7 months ago \| past
4.		First vision language model built off Open AI GPT-OSS (huggingface.co)
		3 points by BUFU 7 months ago \| past
5.		First Multimodal AI Model Designed for NPUs (huggingface.co)
		1 point by BUFU 7 months ago \| past
6.		Nexa AI Blogs (nexa.ai)
		1 point by BUFU 7 months ago \| past
7.		LFM2-VL: Efficient Vision-Language Models (liquid.ai)
		3 points by BUFU 7 months ago \| past
8.		Stanford CS336 Language Modeling from Scratch (youtube.com)
		19 points by BUFU 7 months ago \| past
9.		Ollama's new app (ollama.com)
		560 points by BUFU 8 months ago \| past \| 284 comments
10.		You can now connect a directory of apps and tools to Claude with one click (claude.ai)
		2 points by BUFU 8 months ago \| past \| 1 comment
11.		Ask HN: What tools have you tried to run AI locally on mobile?
		2 points by BUFU 9 months ago \| past
12.		A C++ library to efficiently run Gemma-3N across various platform (github.com/google-ai-edge)
		5 points by BUFU 10 months ago \| past
13.		The Trump-Musk feud has been great for X, which jumped up the App Store charts (techcrunch.com)
		6 points by BUFU 10 months ago \| past \| 1 comment
14.		How we’re responding to The NYT’s data demands in order to protect user privacy (openai.com)
		284 points by BUFU 10 months ago \| past \| 324 comments
15.		ChatGPT Deep Research connects cloud apps (twitter.com/openai)
		1 point by BUFU 10 months ago \| past
16.		Local AI generates highly realistic dialogue from a transcript (yummy-fir-7a4.notion.site)
		3 points by BUFU 11 months ago \| past \| 2 comments
17.		Shroud's Spectre Divide and its developer are shutting down (theverge.com)
		1 point by BUFU on March 13, 2025 \| past
18.		What Went Wrong with Skype? (theverge.com)
		4 points by BUFU on March 7, 2025 \| past \| 1 comment
19.		Anthropic's Recommendations to OSTP for the U.S. AI Action Plan (anthropic.com)
		3 points by BUFU on March 6, 2025 \| past
20.		Quantized DeepSeek R1 Distill Models with Original Model Accuracy (nexa.ai)
		2 points by BUFU on Feb 18, 2025 \| past
21.		Multimodal Model Quantization Support Through LLM Compressor by Neural Magic (neuralmagic.com)
		1 point by BUFU on Feb 17, 2025 \| past
22.		DeepSeek-R1-Distill-Qwen-1.5B Surpasses GPT-4o in certain benchmarks (huggingface.co)
		39 points by BUFU on Jan 20, 2025 \| past \| 17 comments
23.		NexaQuant: Llama.cpp-Compatible Model Compression with 100%+ Accuracy Recovery (nexa.ai)
		3 points by BUFU on Jan 3, 2025 \| past \| 1 comment
24.		Meta's new Video Understanding Multimodal Model used Qwen model for training (arxiv.org)
		7 points by BUFU on Dec 16, 2024 \| past \| 1 comment
25.		Llama.cpp Now Supports Qwen2-VL (Vision Language Model) (github.com/ggerganov)
		155 points by BUFU on Dec 14, 2024 \| past \| 50 comments
26.		OmniAudio-2.6B: Fastest Audio Language Model for Edge Deployment (nexa.ai)
		2 points by BUFU on Dec 13, 2024 \| past \| 1 comment
27.		Moondream 0.5B: The Smallest Vision-Language Model (moondream.ai)
		14 points by BUFU on Dec 5, 2024 \| past \| 3 comments
28.		ShowUI: One Vision-Language-Action Model for GUI Visual Agent (arxiv.org)
		2 points by BUFU on Nov 27, 2024 \| past
29.		What happens if we remove 50 percent of Llama? (neuralmagic.com)
		231 points by BUFU on Nov 26, 2024 \| past \| 132 comments
30.		Run Qwen Audio Language Model on Local Devices for Voice Chat and Audio Analysis (nexa.ai)
		4 points by BUFU on Nov 25, 2024 \| past
		More

HN For You