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.
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 ...
ComfyUI v0.35.0 Released with Comfy Compiler and Memory Fixes
ComfyUI v0.35.0 is out, featuring Comfy Compiler, container memory management improvements, new model support, and AM ...
Unsloth v0.1.808-beta Released: Major Performance Boosts
Unsloth v0.1.808-beta brings significant performance gains for diffusion models, AMD GPUs, and Apple Silicon, alongsi ...
DeepSeek V4.1 Flash: Faster and Cheaper Than V4 Pro
DeepSeek plans to release V4.1 Flash, outperforming V4 Pro at a lower cost, sparking community debate on forced model ...
vLLM v0.29.0 Released: Model Runner V2 Default and More
vLLM v0.29.0 is released with Model Runner V2 as default, FlashInfer all-reduce, new admission control flags, and sup ...
Benchmarking Qwen3.8 27B Quantizations: Performance Analysis
Detailed benchmark results reveal performance changes in Qwen3.8 27B quantizations, showing high performance down to ...
Unsloth v0.1.807-beta Released with AMD and Apple Silicon Boosts
Unsloth v0.1.807-beta is out, bringing major performance boosts for AMD and Apple Silicon, Vulkan defaults, and Windo ...
Irodori-TTS-v4.1-Anime: Our Generated Audio, File List
Discover Irodori-TTS-v4.1-Anime, an anime-style fine-tuned Text-to-Speech model based on Aratako/Irodori-TTS-v4.1-Sma ...