Signal-3.8-27B-GGUF: Our Test Answers, 16GB+ VRAM
Discover Signal-3.8-27B-GGUF, a minimally invasive fine-tune of Qwen3.8-27B offering lower latency, reduced token usa ...
Gryphe_Pantheon-Reasoning-26B-A4B-1.1-V2-GGUF: Our Test Answers
Download bartowski’s GGUF quantizations for Gryphe Pantheon-Reasoning-26B, a Gemma 4 roleplay and reasoning mod ...
Edge0-35B-A3B-preview 35B MoE Model for Phone-Class Memory: 24GB+ VRAM
Edge0 released Edge0-35B-A3B-preview, a 35B sparse MoE model running on phone-class memory using streaming inference. ...
Lightricks Releases Multiple LoRA and IC-LoRA Adapters for LTX-2.5
Lightricks has released multiple LoRA and IC-LoRA adapters for Lightricks/LTX-2.5, enabling character consistency, ci ...
YuE2-3B Music Generation Model for Lyrics and Style: 12GB+ VRAM
m-a-p releases YuE2-3B, an open music generation model using AR-NAR Mixture-of-Transformers to generate 48kHz stereo ...
DeepSeek-V4-Pro-0813-nvfp4-DSpark: ~1005GB Memory
NVIDIA has released nvidia/DeepSeek-V4-Pro-0813-nvfp4-DSpark, a fully NVFP4-quantized MoE language model supporting S ...
ExLlamaV3 v1.4.9 Released: Faster CPU Offloading
ExLlamaV3 v1.4.9 is released with faster CPU offloading, Intel AVX512BW support, and new model architectures.
DeepSeek-V4.1-Flash 552B Multimodal MoE Model: ~570GB Memory
deepseek-ai has released DeepSeek-V4.1-Flash on Hugging Face, a multimodal MoE model supporting up to 1M tokens. Lear ...
H3-to-LTX-Latent-Adapter: 4GB+ VRAM, File List
Discover H3-to-LTX Latent-Adapter, a BF16 inference adapter that converts MiniMax-H3 video latents to LTX-2.5 Conv Vi ...
Does Qwen 3.8 Mimic GPT-5.5 Pro Reasoning Prefills?
Unverified experimental results spark community debate on whether Qwen 3.8 mimics GPT-5.5 Pro’s reasoning proce ...