Follow
Koboldcpp 347
Oct 11 3 days ago 10:05 Upload Qwen-Image-2.1.kcppt Sep 23 21 days ago 12:13 Update starter-pack.kcppt Sep 20 24 days ago 04:10 Update starter-pack.kcppt 04:10 Update starter-pack-v2.kcppt 04:09 Update starter-pack.kcppt Sep 6 23:22 DasiwaH3 Clip on GPU Sep 3 14:48 Upload DasiwaMinimaxH3.kcppt A hybrid of both MinimaxH3 with further enhancements, unlike other Dasiwa models this is not a model with NSFW tuning. Aug 8 01:23 Upload minimax_h3.kcppt Note: Uses a large amount of regular RAM due to the CPU swapping settings we default to, but this is done with mmap by default. So if you can't fit it it should merely stream from disk into your GPU. Jul 15 17:45 BookWriter (Includes Lite save) Unconventional upload for this repository but shows off what kcppt's can do in their full potential.
When you use this kcppt and load up Lite without existing settings we automatically set it up for long story writing.
After loading its best to set the max context slider all the way to the maximum. 17:44 Upload Anima Turbo.kcppt Jun 27 13:53 Rename Krea2.kcppt to Krea2Turbo.kcppt 13:49 Upload 3 files Jun 4 08:30 Update ltx2.3.kcppt May 30 08:34 Upload ltx2.3.kcppt Apr 20 19:56 Upload ace-step-sftturboXL-10GB.kcppt Mar 19 23:06 Delete ace-step-sftturbo-6GB.kcppt 23:05 Music Mar 10 15:38 Upload 2 files Feb 28 12:17 Tight fit config for 6GB, doesn't fit for you? Try the other one Feb 16 14:05 Upload Qwen Image Edit 2511.kcppt Feb 15 14:59 Upload wan_2.2_14b.kcppt Dec 11, 2025 03:16 Upload starter-pack-v2.kcppt Dec 8, 2025 07:16 Upload starter-pack-v2.kcppt Dec 6, 2025 01:43 Upload qwen3-vl-2b.kcppt Dec 4, 2025 13:14 Upload z-image-turbo.kcppt Nov 3, 2025 23:16 Download URL fix 12:03 Bump to Q5, Q4 is to dumb in Qwen Image Edit 11:29 Fix Qwen Image Edit Lora support Nov 1, 2025 15:20 Reduce refusals in Qwen Image 11:39 Upload Qwen Image Edit 2509.kcppt Aug 31, 2025 12:09 Upload GLM-4.5-Air-Ablit-2x24GB.kcpps Aug 26, 2025 13:08 Upload gemma-4b.kcppt Jun 28, 2025 14:09 Upload Flux-Kontext.kcppt Jun 19, 2025 13:56 Rename starter_pack.kcppt to starter-pack.kcppt 13:56 Upload starter_pack.kcppt Jun 14, 2025 09:32 Dedicated audio file transcription config This config prefills whisper large turbo, sets the API file size much higher so your files fit and shows additional instructions in KoboldAI Lite. Apr 13, 2025 08:58 Create README.md Apr 4, 2025 16:43 Deepseek fixes Apr 1, 2025 16:58 Update deepseek-r1-500gbofvram.kcppt 15:49 Fix incorrect variable Mar 23, 2025 02:10 Upload Gemma-3-27B-it-abliterated.kcppt Mar 15, 2025 16:08 Upload Gemma-3-27B-it.kcppt 15:52 Upload Gemma-3-27B-it.kcppt 15:17 Fix two gemma 3 27b settings Mar 9, 2025 19:06 Upload QwQ-32B-Abliterated.kcppt Mar 6, 2025 19:26 Increased gen amount for chat adapters 19:05 Upload QwQ-32B.kcppt Mar 2, 2025 16:20 Enable think insertion This is now possible and recommended by Deepseek Feb 19, 2025 15:32 Upload deepseek-r1-500gbofvram.kcppt Feb 18, 2025 18:17 Upload deepseek-r1-500gbofvram.kcppt 
