view post Post 8023 Qwen3.8 - 27B - COLD FUSION Reduction in thinking tokens to 1/10 to 1/2 "normal Qwen" across all three modes of thinking without loss of detail in thinking or output.Increase in general intelligence too (all 7 critical benches); bench marks posted.Trained using the COLD FUSION method (GAIN + UNSLOTH).NOTE: This is NOT a heretic / uncensored version.MTP and GGUF NEO MAX quants: DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUFSOURCE: DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 See translation 3 replies · 👍 14 14 🔥 12 12 🤝 5 5 🧠 3 3 🚀 2 2 + Reply
view post Post 6274 We're excited to open source BananaMind OS, our OS for running BananaMind models.It allows you to run local AI on hardware such as a 486 or 386 (untested)Check it out at: https://github.com/BananaMind/BananaMindOSHow to use it, either build it yourself (see instructions on repo) or check out our prebuilt ISOs:https://github.com/BananaMind/BananaMindOS/releases/download/v0.0.2/bananamind-os.iso is for 6MB+ RAM using Grubhttps://github.com/BananaMind/BananaMindOS/releases/download/v0.0.2/bananamind-ultra.iso is for under 6MB RAM using our custom bootloader to bypass the grub memory requirement.The ISOs are about 70MB because they include all of the models in our custom format, see repo if you want to build a ISO for only one model.x64 and x86 supported. 16 bit maybe soon.And a TTS on 486 soon. See translation 9 replies · 🔥 12 12 + Reply
DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF Image-Text-to-Text • 27B • Updated about 21 hours ago • 177k • 187
Blackfrost-AI/Qwen3.8-27B-ABLITERATED-GGUF Image-Text-to-Text • 27B • Updated about 4 hours ago • 203k • 205
yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF Text Generation • 12B • Updated Jun 19 • 407k • 1.48k
huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated Image-Text-to-Text • 27B • Updated Jul 12 • 39.3k • • 59