Uncensored DeepSeek-V4.1-Flash IQ2_XS on Google Colab
Like leonxger/deepseek-colab, 0 likes 0 Bookmark leonxger/deepseek-colab, 0 bookmarks 0 A custom inference engine tuned for Qwen4 architecture. Currently runs Qwen3.8-Flash-Next at 15+ tok/s on 16GB of VRAM and 30 GB of RAM
Like Apolog1ze-Dev/QwFNfer, 0 likes 0 Bookmark Apolog1ze-Dev/QwFNfer, 0 bookmarks 0 Self-hosted vLLM inference for Qwen3.6-35B-A3B-NVFP4
Like MiaAI-Lab/Qwen3.6-35B-A3B-NVFP4-vLLM, 0 likes 0 Bookmark MiaAI-Lab/Qwen3.6-35B-A3B-NVFP4-vLLM, 0 bookmarks 0 qwen38-flash-next recipe for solo GB10
Like myllmbox/qwen38-flash-next-recipe, 0 likes 0 Bookmark myllmbox/qwen38-flash-next-recipe, 0 bookmarks 0 A local app that rents a GPU in your own Colab account and serves Qwen3.8 on it: 27B on an A100-40G, or Flash-Next (125B-A6B MoE) on an A100-80G. The cost is shown before it starts; chat with images; Codex or any OpenAI client uses a fixed local /v1. Auto-stop, CU ledger, live prefill/decode. Windows, macOS, Linux.
Like architectds/collabosm, 0 likes 0 Bookmark architectds/collabosm, 0 bookmarks 0 Qwen3.8 Flash Next on one DGX Spark (TensorFold)
Like MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold, 0 likes 0 Bookmark MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold, 0 bookmarks 0 Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux
Like MiaAI-Lab/Qwen3.8-27B-16gb-NVIDIA-GPUs-one-click-install, 0 likes 0 Bookmark MiaAI-Lab/Qwen3.8-27B-16gb-NVIDIA-GPUs-one-click-install, 0 bookmarks 0 Qwen3.8-Flash-Next (125B MoE) up to 1M context on one or two RTX cards (tuned on 3080 10gb). A measured, tuned and benchmarked fork of Strata.
Like DevDock-AI/Speedy, 0 likes 0 Bookmark DevDock-AI/Speedy, 0 bookmarks 0 Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.
Like Mesh-LLM/mesh-llm, 0 likes 0 Bookmark Mesh-LLM/mesh-llm, 0 bookmarks 0