/technology
/lmg/ - a general dedicated to the discussion and development of local language models. News >(10/31) Index Translate 9B, multilingual text model built on Qwen 3.5: https://hf.co/IndexTeam/Index-Translate-9Bβ§ >(10/29) Mistral Large 4 (Le Chonk) 1T-A52B released: https://mistral.ai/news/mistral-large-4-ossβ§ >(10/27) NVidia releases Nemotron 3.5 Transcribe 30B-A4B: https://hf.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4Bβ§ >(10/26) XHToken releases Spark-X2.6-1.7B: https://hf.co/XHToken/Spark-X2.6-1.7Bβ§ >(10/26) LiquidAI releases LFM3 1.7B and 2B: https://hf.co/collections/LiquidAI/lfm3β§ News Archive: https://rentry.org/lmg-news-archiveβ§ Links: https://rentry.org/LocalModelsLinksβ§ Official /lmg/ card: https://files.catbox.moe/cbclyf.pngβ§ Getting Started https://rentry.org/lmg-lazy-getting-started-guideβ§ https://rentry.org/lmg-build-guidesβ§ https://rentry.org/IsolatedLinuxWebServiceβ§ https://rentry.org/recommended-modelsβ§ https://rentry.org/samplersβ§ https://rentry.org/MikupadIntroGuideβ§ Further Learning https://rentry.org/machine-learning-roadmapβ§ https://rentry.org/llm-trainingβ§ https://rentry.org/LocalModelsPapersβ§ Benchmarks LiveBench: https://livebench.aiβ§ Programming: https://swe-rebench.comβ§ Agentic Coding: https://deepswe.datacurve.aiβ§ Context Length: https://github.com/RecapAnon/NoLiMaβ§ GPUs: https://github.com/XiongjieDai/GPU-Benchmarks-on-LLM-Inferenceβ§ Tools GGUF VRAM Calculator: https://hf.co/spaces/NyxKrage/LLM-Model-VRAM-Calculatorβ§ Sampler Visualizer: https://artefact2.github.io/llm-samplingβ§ Token Speed Visualizer: https://shir-man.com/tokens-per-secondβ§ Text Gen. UI, Inference Engines https://github.com/lmg-anon/mikupadβ§ https://github.com/oobabooga/text-generation-webuiβ§ https://github.com/LostRuins/koboldcppβ§ https://github.com/ggerganov/llama.cppβ§ https://github.com/theroyallab/tabbyAPIβ§ https://github.com/vllm-project/vllmβ§ https://rentry.org/custom-uisβ§β± 1wβ© 49
inference is experienceβ± 1wβ©
+ 48