Breaking the 1.58-bit Barrier for Ternary LLMs with BITCOS
A research paper proposes BITCOS, achieving 1.485 bits/weight in ternary LLMs by exploiting weight distribution skew ...
TensorRT Edge-LLM Accelerates MLPerf Agentic Benchmark
NVIDIA tests TensorRT Edge-LLM with Qwen3.6-27B on Jetson AGX Thor, achieving a 6.4x speedup over llama.cpp in MLPerf ...
Qwen-2.5-1B-RLCD Text Generation Model: 4GB+ VRAM
Explore harshatheg/Qwen-2.5-1B-RLCD, an MLX implementation using parallel constrained decoding on Apple Silicon for h ...
Unsloth Now Supports Windows ARM64 for Local LLMs
Unsloth releases Windows ARM64 binaries, enabling local LLM execution and fine-tuning on ARM-based Windows devices.
EleutherAI Releases OLMo-3-7B Models for Reward-Hacking Research
EleutherAI releases two OLMo-3-7B models trained via GRPO to study reward-hacking dynamics and validate the hack-igni ...
Why Tech Community is Debating Bearish Views on LLMs
A personal blog post arguing against the autonomous future of LLMs sparks intense debate in the tech community on Hac ...
ComfyUI v0.36.0 Released: Generic Loops, Yue2 & Marigold v2
ComfyUI v0.36.0 is out, introducing Generic Loops, support for Yue2 and Marigold v2, Llama RoPE speedups, AMD improve ...
koboldcpp v1.121 Released: New Features & Bug Fixes
koboldcpp v1.121 is out with Minimax H3 media reference support, revamped MusicUI, runtime LoRA selectors in SDUI, an ...
vectionlabs_Salience-27B-R6-GGUF: Our Test Answers, 12GB+ VRAM
bartowski has released GGUF quantizations for Vection Labs’ Salience-27B-R6, a multimodal 27B Dense model with ...
Intern-S2-397B-GGUF Vision-Language Model: ~102GB Memory
Discover bartowski/Intern-S2-397B-GGUF, a multimodal foundation model quantized for local inference using llama.cpp.