Nemotron-3.5-Bolt-E4B-Artemis-FP8
Tested with vLLM 0.32.0rc1 (a development build). Every result below was measured with thinking off; BFCL-v3 ran at...
Tested with vLLM 0.32.0rc1 (a development build). Every result below was measured with thinking off; BFCL-v3 ran at...
LithosAI · draft model for lossless speculative decoding with Kimi-K3.1-Pro A DSpark draft head. In each decode step...
Добро пожаловать в серию Loopie, самый мощный на сегодняшний день петлевой трансформатор с открытым исходным кодом, обученный IQuest...
A Blackfrost derisked derivative of NVIDIA Nemotron-3.5 Bolt 74B-A9B, built for professional cybersecurity work: false-refusal friction on legitimate...
4-bit GPTQ build of LiquidAI/LFM2.5-24B-A2B, built to serve an office of agents from one RTX 4000 Ada 20...
This repository contains the DCOCO (DFlash Contextual Corrector) speculative-decoding drafter for NVIDIA Nemotron 3.5 Super VL 120B-A12B, from...
A 27B model that texts like a person and still does the work, in FP8 for 32 to...
This is UkisAI’s Swift 1.5 Qwen3.8-Flash-Next AutoRound W4A16 checkpoint, repackaged to match the layout of albucino/Qwen3.8-Flash-Next-W4A16-FP8PLE. That layout...
Original model by Naive AI. This release is built on their work. The Naive AI team created and...
Unofficial 4-bit GPTQ quantization of Altworld/Hemmingway-1 for low-VRAM inference, with the MTP (multi-token-prediction) draft head deliberately kept unquantized....