e9931084b5ac — bitchan

𓁟 host1.bitchan.one

𓀐 @by2krySN

⏱ 5d seen⛓ 0👍 0⧖ 1

filter [-]

languages:onother

/lmg/ - a general dedicated to the discussion and development of local language models. News >(11/01) Longcat-2.5 released: https://longcat.ai/blog/longcat-2.5 >(10/30) Google receives response from Gemma in space: https://blog.google/innovation-and-ai/models-and-research/google-research/project-suncatcher-satellite-response >(10/29) Mistral Large 4 (Le Chonk) 1T-A52B released: https://mistral.ai/news/mistral-large-4-oss >(10/27) NVidia releases Nemotron 3.5 Transcribe 30B-A4B: https://hf.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B >(10/26) XHToken releases Spark-X2.6-1.7B: https://hf.co/XHToken/Spark-X2.6-1.7B News Archive: https://rentry.org/lmg-news-archive Links: https://rentry.org/LocalModelsLinks Official /lmg/ card: https://files.catbox.moe/cbclyf.png Getting Started https://rentry.org/lmg-lazy-getting-started-guide https://rentry.org/lmg-build-guides https://rentry.org/IsolatedLinuxWebService https://rentry.org/recommended-models https://rentry.org/samplers https://rentry.org/MikupadIntroGuide Further Learning https://rentry.org/machine-learning-roadmap https://rentry.org/llm-training https://rentry.org/LocalModelsPapers Benchmarks LiveBench: https://livebench.ai Programming: https://swe-rebench.com Agentic Coding: https://deepswe.datacurve.ai Context Length: https://github.com/RecapAnon/NoLiMa GPUs: https://github.com/XiongjieDai/GPU-Benchmarks-on-LLM-Inference Tools GGUF VRAM Calculator: https://hf.co/spaces/NyxKrage/LLM-Model-VRAM-Calculator Sampler Visualizer: https://artefact2.github.io/llm-sampling Token Speed Visualizer: https://shir-man.com/tokens-per-second Text Gen. UI, Inference Engines https://github.com/lmg-anon/mikupad https://github.com/oobabooga/text-generation-webui https://github.com/LostRuins/koboldcpp https://github.com/ggerganov/llama.cpp https://github.com/theroyallab/tabbyAPI https://github.com/vllm-project/vllm https://rentry.org/custom-uis⏱ 5d↩ 38

Recent Highlights from the --Collaborative neuron census project for total interpretability of Gemma4-31b-it: >110229560 >110229610 >110229674 >110229619 --Feasibility of clustering CPU nodes for high-bandwidth tensor parallelism: >110227909 >110227921 >110227987 >110228005 >110228046 >110228002 --Applying GRPO and RL to improve Orb prose and autocomplete models: >110227271 >110227291 >110227466 --Unsloth v3.1 GGUFs outperforming GSQ-RCO in agentic benchmarks: >110229401 --Rumors of Alibaba ending open-source small-base Qwen models: >110227317 >110227420 >110227478 >110228719 >110228823 >110227426 >110227519 >110227613 >110227778 --Anon's AMD Radeon AI Pro R9700 purchase and AMD performance discussion: >110226718 >110228087 >110228130 >110226819 >110226868 >110226840 >110226869 >110229882 --Using weight-space programming for cloud-to-local model distillation: >110229697 >110229820 --Comparing model personalities and censorship during roleplay tests: >110226496 >110226603 >110226615 >110226994 --Maya releases GLM-5.3-Flash quant with high VRAM requirements: >110229752 >110229764 >110229790 --Comparing history search and compaction boundary features in model harnesses: >110225976 --Effectiveness of abliteration for removing refusals and repetitive patterns: >110225709 >110226069 --Discussion on nv-uefi-unlocker and risks of unofficial GPU firmware: >110225574 >110225581 >110225647 --LongCat-2.5 release and llama.cpp compatibility query: >110229298 >110229314 --Logs: >110225820 >110226603 --Deepseek-chan, Gemma, Miku (free space): >110225016 >110225105 >110225194 >110225360 >110225421 >110226079 >110226670 >110226712 >110226782 >110227119 >110227411 >110227446 >110227501 >110227561 >110227618 >110228667 >110228893 >110229161 >110229200 >110229625 >110229725 >110229954 >110229956 >110230052 >110230212 Recent Highlight Posts from the Why?: Enable Links: https://rentry.org/lmg-recap-script⏱ 5d↩