Topics
Results for “quantization”
70 results
- chatrlabs/Qwen-Image-2.1-Uncensored-Omni-Quantized — Hugging Face Models · Seen
- Edge0/Edge0-145B-NVFP4 — Hugging Face Models · Seen
- meituan-longcat/LongCat-2.5 — Hugging Face Models · Seen
- taobao-mnn/MNN-Pocket-0.3B — Hugging Face Models · Seen
- mradermacher/gemma-4-31B-it-ARA-heretic-GGUF — Hugging Face Models · Seen
- abenzerps/Qwen-Image-2.1-Turbo-Quantized — Hugging Face Models · Seen
- DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF — Hugging Face Models · Seen
- AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-GGUF — Hugging Face Models · Seen
- huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF — Hugging Face Models · Seen
- black-forest-labs/flux-3-image-klein-comfy — Hugging Face Models · Seen
- SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF — Hugging Face Models · Seen
- ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF — Hugging Face Models · Seen
- unsloth/Qwen3.8-27B-GGUF — Hugging Face Models · Seen
- MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations — Hugging Face Papers · Seen · 32 points
- Comfy-Org/MiniMax-H3 — Hugging Face Models · Seen
- LiquidAI/Liquid-Codec — Hugging Face Models · Seen
- Advancing Quantization for R&R Models with Microscaling Formats — arXiv AI Papers · Seen
- Does the Ranking Hold? A Practitioner-Facing Audit of Hallucination Detectors on Small, Quantized, On-Device LLMs — arXiv AI Papers · Seen
- G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation — 2 sources · Seen · 46 points
- PrunaAI/P-H3-Image-Comfy — Hugging Face Models · Seen
- ggml-org/ggml — 2 sources · Seen
- Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update — Hacker News · Seen · 254 points
- Scantist/GLM-5.3-SLIM-GGUF — Hugging Face Models · Seen
- I'm making LLMs work on small and old devices — Hacker News · Seen · 477 points
- Huawei releases MACaQ, its internal quantizer for local inference — Hacker News · Seen · 134 points
- ggml-org/llama.cpp — GitHub Trending · Seen
- mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF — Hugging Face Models · Seen
- mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF — Hugging Face Models · Seen
- autotrust/Qwen3.8-Flash-Next-E384-FP4-V2 — Hugging Face Models · Seen
- Compress any LLM 3x in one click, near-lossless, in under 50 MB RAM — Hacker News · Seen · 21 points
- Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU — Hacker News · Seen · 470 points
- I Retested My MoE Offloading Benchmarks. Some of My Conclusions Changed. — DEV Community · Seen
- nvidia/DeepSeek-V4.1-Flash-1017-NVFP4 — Hugging Face Models · Seen
- unsloth/DeepSeek-V4.1-Flash-1017-GGUF — Hugging Face Models · Seen
- AtomicChat/LFM3-1.7B-Uncensored-GGUF — Hugging Face Models · Seen
- ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF — Hugging Face Models · Seen
- VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video Generation — arXiv AI Papers · Seen
- LiquidAI/LFM3-1.7B-GGUF — Hugging Face Models · Seen
- Accuracy vs Speed: Gemma 4 E2B Quantization Tradeoffs, BF16 to Q2_K — DEV Community · Seen
- orcarouter/DeepSeek-V4.1-Flash-1017-abliterated-GGUF — Hugging Face Models · Seen
- abenzerps/Qwen-Image-2.1-Uncensored-Quantized — Hugging Face Models · Seen
- Bitnet.cpp: Efficient Edge Inference for Ternary LLMs — Hugging Face Papers · Seen · 18 points
- Show HN: A language model that lives in a boot sector — Hacker News · Seen · 105 points
- dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8 — Hugging Face Models · Seen
- Comfy-Org/MOSS-Image — Hugging Face Models · Seen
- ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF — Hugging Face Models · Seen
- Predicate Neuron: Differentiable Quantization of Predicate Relations in Gradient-based Learning — arXiv AI Papers · Seen
- Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals? — Hugging Face Papers · Seen · 90 points
- 3 Ways to Boost MoE Inference on NVIDIA DGX Spark — NVIDIA Developer Blog · Seen
- ResCom: Activation Residual Compensation for Large Language Model Quantization — arXiv AI Papers · Seen
- Comfy-Org/Fibo-2.0 — Hugging Face Models · Seen
- AGQ: Action-Guided Ultra-Low-Bit Quantization for Vision-Language-Action Models — arXiv AI Papers · Seen
- Every Weight Is a Path of Shared Discrete Decisions — Hugging Face Papers · Seen · 23 points
- nvidia/GLM-5.3-Flash-FP4-Local — Hugging Face Models · Seen
- Spike-Aware Gradient-Based Mixed-Precision Quantization of Spiking Neural Networks for Vision Applications — arXiv AI Papers · Seen
- nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 — Hugging Face Models · Seen
- black-forest-labs/flux-3-image-klein-base — Hugging Face Models · Seen
- nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB — Hugging Face Models · Seen
- ConwayResearch/Underdog-Saluki-27B-1.0 — Hugging Face Models · Seen
- LiquidAI/LFM2.5-24B-A2B-GGUF — Hugging Face Models · Seen