Submissions from huggingface.co

		Continuous batching from first principles (2025) (huggingface.co)
		29 points by jxmorris12 7 hours ago \| past \| 6 comments
		PersonaPlex-7B: full-duplex voice model that listens and talks at the same time (huggingface.co)
		2 points by MrBuddyCasino 14 hours ago \| past \| discuss
		Custom Kernels for All from Codex and Claude (huggingface.co)
		1 point by microtonal 2 days ago \| past \| discuss
		MiniMax M2.5 weights (huggingface.co)
		4 points by tosh 2 days ago \| past \| discuss
		Outperforming AWS Comprehend in a Weekend (huggingface.co)
		1 point by TylerOvermind 2 days ago \| past \| discuss
		OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World Environments (huggingface.co)
		1 point by ibobev 2 days ago \| past \| discuss
		Multi-vector Grep for code agents, save 15% tokens, local (huggingface.co)
		3 points by raphaelty 3 days ago \| past \| 1 comment
		Can LLMs Play the Game of Science? (huggingface.co)
		1 point by amai 4 days ago \| past \| discuss
		Transformers.js v4 Preview: Now Available on NPM (huggingface.co)
		1 point by ibobev 4 days ago \| past \| discuss
		From Golden Gate Bridge to JSON: Why Anthropic's SAE Failed on JSON Output (huggingface.co)
		2 points by maziyar 5 days ago \| past \| 1 comment
		The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+ (huggingface.co)
		2 points by mariuz 5 days ago \| past \| discuss
		LingBot – open weights world model (huggingface.co)
		1 point by nikhizzle 5 days ago \| past \| discuss
		MechaEpstein-8000 (huggingface.co)
		1 point by aortega 5 days ago \| past \| 1 comment
		Show HN: Insurance AI Benchmark – 510 scenarios from production (huggingface.co)
		1 point by pavelsukhachev 6 days ago \| past \| discuss
		PaperBanana: Automating Academic Illustration for AI Scientists (huggingface.co)
		2 points by 7777777phil 6 days ago \| past \| discuss
		Sanskrit AI beats CleanRL SOTA by 125% (huggingface.co)
		1 point by prabhatkr 8 days ago \| past \| 1 comment
		The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+ (huggingface.co)
		6 points by gmays 8 days ago \| past \| discuss
		Benchmarking how well LLMs can play FizzBuzz (huggingface.co)
		2 points by _venkatasg 9 days ago \| past \| 1 comment
		I trained a 135M TTS model for ~$100, runs 20× real-time on CPU (huggingface.co)
		4 points by sammyyyyyyy 9 days ago \| past \| 2 comments
		Craft – image models can think like LLMs (huggingface.co)
		5 points by denti 10 days ago \| past \| 1 comment
		Sopro v1.5: A 135M TTS model trained for ~$100, runs 20× real-time on CPU (huggingface.co)
		5 points by sammyyyyyyy 10 days ago \| past \| 1 comment
		Show HN: DeepBrainz-R1 – Reasoning-First Small Models for Agentic Systems (huggingface.co)
		3 points by DeepBrainz 10 days ago \| past \| discuss
		The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+ (huggingface.co)
		1 point by myk-e 12 days ago \| past \| discuss
		Qwen3-coder-next: SOTA open source coding model (huggingface.co)
		3 points by binsquare 12 days ago \| past \| discuss
		Zai/GLM-OCR (huggingface.co)
		2 points by naze 13 days ago \| past \| 1 comment
		Step 3.5 Flash LLM model, agentic coding ~18x faster than GLM 4.7 / Kimi K2.5 (huggingface.co)
		3 points by skhameneh 13 days ago \| past \| 1 comment
		Post anything on Moltbook as a human, without AI (huggingface.co)
		2 points by shash42 13 days ago \| past \| 1 comment
		One Year Since the "DeepSeek Moment" (huggingface.co)
		3 points by myk-e 14 days ago \| past
		VibeVoice-ASR: speech-to-text model designed to handle 60-minute long-form audio (huggingface.co)
		11 points by maxloh 15 days ago \| past
		Nvidia Nemotron 3-Nano 30B-A3B-BF16 (huggingface.co)
		10 points by tosh 15 days ago \| past \| 1 comment
		More