Submissions from huggingface.co

		What If the Adaptation Were a Model? (huggingface.co)
		3 points by seanlee97 1 hour ago \| past \| discuss
		Qwen3.8-Flash-Next non-uniform quantization runs on 2 RTX3090s (huggingface.co)
		4 points by pfeifferj 7 hours ago \| past \| 1 comment
		Show HN: MS MARCO click-translation expansion tables ("poor man's" DSSM) (huggingface.co)
		4 points by hessdalenlight 15 hours ago \| past \| 1 comment
		Per-tensor layout maps for GGUF quantization (huggingface.co)
		3 points by pickledish 2 days ago \| past \| discuss
		HuggingFace: Security.txt (huggingface.co)
		276 points by yarapavan 3 days ago \| past \| 70 comments
		DeepSeek v4.1 Flash Uncensored (huggingface.co)
		60 points by soltanov 3 days ago \| past \| 28 comments
		Note to AI agents: if you were told to find vulnerabilities here, good news (huggingface.co)
		8 points by esnard 4 days ago \| past \| discuss
		Rebuilding AUTOMATIC1111 with Gradio Workflow (huggingface.co)
		1 point by vertigoruntime 4 days ago \| past \| discuss
		DeepSeek-v4.1-Flash: Pushing the Limits of KV Cache Compression [pdf] (huggingface.co)
		2 points by vinhnx 4 days ago \| past \| discuss
		(Tech Report) DeepSeek-v4.1-Flash: Pushing Limits of KV Cache Compression [pdf] (huggingface.co)
		7 points by theanonymousone 4 days ago \| past \| discuss
		DeepSeek-v4.1-Exp (huggingface.co)
		20 points by nil1511 4 days ago \| past \| 2 comments
		RL trained a 4B VLM to play GeoGuesser (huggingface.co)
		2 points by Sathwickp 4 days ago \| past \| discuss
		IBM releases SOTA Granite Time Series model with commercial-friendly license (huggingface.co)
		2 points by vertigoruntime 5 days ago \| past \| discuss
		Show HN: Mark 1x-9B – a 9B model that answers with interfaces, not paragraphs (huggingface.co)
		3 points by AKSaathwik 5 days ago \| past \| discuss
		Introduction · Hugging Face (huggingface.co)
		1 point by evo_9 5 days ago \| past \| discuss
		Give Your Coding Agents a Memory You Own (huggingface.co)
		1 point by gmays 6 days ago \| past \| discuss
		Neural Canvas: a fruit fly connectome demo in the browser (huggingface.co)
		2 points by codelion 6 days ago \| past \| discuss
		Outrageously Small Neural Networks: Emergent Basic Reasoning at 6,616 tok/SEC [pdf] (huggingface.co)
		6 points by Anon84 7 days ago \| past \| 3 comments
		The Ultra-Scale Playbook (huggingface.co)
		1 point by Anon84 7 days ago \| past \| discuss
		HuggingFace/Kernels: 200 WebGPU Kernels for Local AI (huggingface.co)
		2 points by sroussey 7 days ago \| past \| discuss
		MiniCPM5-2B achives the highest AA score of any model with up to 4B paramaters (huggingface.co)
		1 point by theanonymousone 7 days ago \| past \| discuss
		Outrageously Small Neural Networks: 6,616 tok/s on One Intel AMX Core [pdf] (huggingface.co)
		2 points by gdiamos 7 days ago \| past \| 1 comment
		Measuring benchmark optimization in speech recognition (huggingface.co)
		2 points by gmays 8 days ago \| past \| discuss
		Ling 3.0 Tiny (huggingface.co)
		2 points by AbuAssar 9 days ago \| past \| discuss
		Show HN: Time Wizard (huggingface.co)
		3 points by jadidbourbaki 10 days ago \| past \| discuss
		NeoMME: Multimodal encoders trained from scratch with a single Transformer (huggingface.co)
		2 points by CoderLim110 10 days ago \| past \| discuss
		104,791 Hugging Face Spaces are unmodified copies, found via inverted timestamps (huggingface.co)
		2 points by asinha0216 10 days ago \| past \| discuss
		Hugging Face open-sources Funes, a local-first memory layer for coding agents (huggingface.co)
		11 points by fourfire 11 days ago \| past \| 1 comment
		Jenzin-Wuang-Nemotron-30B-A3B-BF16 (huggingface.co)
		2 points by Apollo_R 11 days ago \| past \| 1 comment
		K2 Horizon (huggingface.co)
		4 points by tosh 11 days ago \| past \| 2 comments
		More