# Open-Weight Models Under unknown: Open-Weight AI Source: https://savrn.com/models/licenses/unknown Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub · Models by License # Open-Weight Models Under unknown 32 open-weight models released under unknown in the SAVRN Model Hub, with Kachadoorian, Yong Jia Choo and Ian publishing the most. 32Models 20Publishers 17K to 23MParameter range 1Licenses ## SAVRN's Take There is no summary of commercial use on this page, and that absence is the whole subject. Five models sit here because their publishers attached no license we could name, so SAVRN does not summarize terms for them, and whatever text the publisher put with the weights governs. For an operator, the question stops being what the license allows and becomes whether there is one at all. You can put the files on your racks, but when a customer or your counsel asks what permits that, an empty field is not an answer. The mist checkpoints show how this happens: their Zenodo deposit, record 8316682, tags them only as other-open with no exact terms identified, and the MIT license on the software does not reach the weights. Code and checkpoints are licensed separately, so get the weights text in writing before serving anything from this group to a customer. Five publishers hold one model each: Chris Cole, User Android, Kachadoorian, AlexSorbin and the Computational Metabolomics Research Group. Almost all the traffic is LTX-2.3-uncensored-v1.4-FP8 at 65,861 downloads a month, a text-to-video build in GGUF and FP8 with three fine-tunes merged into the weights, one of them an NSFW LoRA by the publisher's description. testinglabsgen sees 7, and Linny-Voice-VITS-Gen2, pocketpet-foundation-checkpoints and mist sit at zero. None of the five lists a parameter count, a context length or a hardware profile, so there is nothing to size a server against yet. SAVRN Research, 2026-09-18 ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [LTX-2.3-uncensored-v1.4-FP8](https://savrn.com/models/ltx-2-3-uncensored-v1-4-fp8) | Chris Cole | — | unknown | 65.9k | — | | [flux2-klein-GGUF](https://savrn.com/models/flux2-klein-gguf) | Chris Cole | — | unknown | 1.8k | — | | [comfyui-models](https://savrn.com/models/comfyui-models-2) | Claudio César Sánchez Tejeda | — | unknown | 31 | — | | [zolai-qwen2.5-3b-lora](https://savrn.com/models/zolai-qwen2-5-3b-lora) | Peter Pau Sian Lian | — | unknown | 23 | — | | [Zelretchv5](https://savrn.com/models/zelretchv5) | Yong Jia Choo | — | unknown | 13 | — | | [testinglabsgen](https://savrn.com/models/testinglabsgen) | User Android | — | unknown | 7 | — | | [Linny-Voice-VITS-Gen2](https://savrn.com/models/linny-voice-vits-gen2) | Kachadoorian | — | unknown | — | — | | [pocketpet-foundation-checkpoints](https://savrn.com/models/pocketpet-foundation-checkpoints) | AlexSorbin | — | unknown | — | — | | [mist](https://savrn.com/models/mist) | Computational Metabolomics Research Group | — | unknown | — | — | | [Engineer](https://savrn.com/models/engineer) | Elliott Buxton | — | unknown | — | — | ## Who Publishes Them | Publisher | Models | | --- | --- | | [Kachadoorian](https://savrn.com/model-publishers/lucien-shark) | 9 | | [Yong Jia Choo](https://savrn.com/model-publishers/marx23411) | 3 | | [Ian](https://savrn.com/model-publishers/wondolls) | 2 | | [Chris Cole](https://savrn.com/model-publishers/chriscoletech) | 2 | | [Elliott Buxton](https://savrn.com/model-publishers/snazzyartist22) | 1 | | [Xiekun](https://savrn.com/model-publishers/shayudabiaoge) | 1 | ## All 32 Models Model · Text to video ### [LTX-2.3-uncensored-v1.4-FP8](https://savrn.com/models/ltx-2-3-uncensored-v1-4-fp8) [Chris Cole](https://savrn.com/model-publishers/chriscoletech) UPDATED 8/21/2026 - The latest LTX Video-2.3 Uncensored Turbo v1.4 DiT with Distilled LoRA baked in. Modes: img2video, txt2video, FL2VA / T2VA / I2VA / REF2VA/ AUDIO-TO-VIDEO. A pre-merged, GGUF and FP8 build of LTX Video-2.3 with three fine-tunes baked into the weights: 1. Eros10 NSFW LoRA - Eros10 is known for high quality, coherence, and NSFW (1.0 strength) 2. DMD Distilled LoRA - DMD distilled LoRA promises faster generations, better facial preservation (I2V), and MUCH better instruction following than v1 or stock LTXV23. (1.0 strength) 3. LTX Video ICLoRA Detailer - Official LTXV In-Context LoRA for better reference image adherence. (0.6 strength) The model can produce video in as… Open weights unknown gguf [View model](https://savrn.com/models/ltx-2-3-uncensored-v1-4-fp8) Model · Text to image ### [flux2-klein-GGUF](https://savrn.com/models/flux2-klein-gguf) [Chris Cole](https://savrn.com/model-publishers/chriscoletech) 9B step-distilled text-to-image — 4 inference steps, ~8s per 1024² image on an A100. One source, three prompts, identical settings — so the difference you see is the prompt. This model's txt2img preset is 4 steps — it is a distilled 4-step model and that is correct for text-to-image. Running img2img at 4 steps produces output indistinguishable from the source at every strength from 0.3 to 0.9: there is not enough schedule left to restyle anything. At 24 steps with guidance 4.0 — the settings this repo's own img2img integration test uses — it restyles properly. The three results above are the same photograph as oil, watercolour and pencil, with the composition intact in each and the medium… Open weights unknown [View model](https://savrn.com/models/flux2-klein-gguf) Model ### [comfyui-models](https://savrn.com/models/comfyui-models-2) [Claudio César Sánchez Tejeda](https://savrn.com/model-publishers/demonccc) Open weights unknown [View model](https://savrn.com/models/comfyui-models-2) Model · Text generation ### [zolai-qwen2.5-3b-lora](https://savrn.com/models/zolai-qwen2-5-3b-lora) [Peter Pau Sian Lian](https://savrn.com/model-publishers/peterpausianlian) LoRA / QLoRA adapter fine-tuned for Tedim Zolai (Zo; ZVS 2018 orthography) generation and bilingual Zo↔English assistance. Part of the Zolai-AI project — a RAG-first bilingual AI toolkit to preserve and teach Tedim Zolai. Generated and curated Zolai text for this project follows Tedim ZVS 2018: - Prefer native-speaker review for dialect naturalness; Hakha forms must not be treated as Tedim ZVS. - Generate / continue Tedim Zolai text under ZVS 2018 norms - Assist Zo↔English drafting (dictionary / parallel-corpus style tasks) - Experimentation for low-resource Tibeto-Burman NLP research - Load as a PEFT adapter on Qwen/Qwen2.5-3B-Instruct for apps, tutors, or RAG-backed bots (e.g. zolai.space… Open weights unknown peft [View model](https://savrn.com/models/zolai-qwen2-5-3b-lora) Model · Text to image ### [Zelretchv5](https://savrn.com/models/zelretchv5) [Yong Jia Choo](https://savrn.com/model-publishers/marx23411) very awa, masterpiece, best quality, absurdres, perfect quality, detailed background, intricate details lowres, worst quality, bad quality, bad anatomy, signature, username, logo, watermark, artist name, bad hands You should use Zelretch22 to trigger the image generation. Download them in the Files & versions tab. Open weights unknown diffusers [View model](https://savrn.com/models/zelretchv5) Model ### [testinglabsgen](https://savrn.com/models/testinglabsgen) [User Android](https://savrn.com/model-publishers/randomuserads) Open weights unknown [View model](https://savrn.com/models/testinglabsgen) Model ### [AGENT](https://savrn.com/models/agent) [DHIVYA T](https://savrn.com/model-publishers/dhivz) Open weights unknown [View model](https://savrn.com/models/agent) Model ### [arnkwoman](https://savrn.com/models/arnkwoman) [Oleksandr Kosminskyi](https://savrn.com/model-publishers/saniakosmos) Open weights unknown [View model](https://savrn.com/models/arnkwoman) Model ### [ayunea2olite](https://savrn.com/models/ayunea2olite) [Ian](https://savrn.com/model-publishers/wondolls) Open weights unknown [View model](https://savrn.com/models/ayunea2olite) Model ### [beastierated](https://savrn.com/models/beastierated) [MARK SIMISTER](https://savrn.com/model-publishers/brsimmo) Open weights unknown [View model](https://savrn.com/models/beastierated) Model ### [clip-multitask-v3](https://savrn.com/models/clip-multitask-v3) [Matthew Johnson](https://savrn.com/model-publishers/matthewjohns) Open weights unknown 16,576 parameters [View model](https://savrn.com/models/clip-multitask-v3) Model ### [Engineer](https://savrn.com/models/engineer) [Elliott Buxton](https://savrn.com/model-publishers/snazzyartist22) Open weights unknown [View model](https://savrn.com/models/engineer) Model ### [hw1-hc3-detector](https://savrn.com/models/hw1-hc3-detector-19) [Adithyaa Veerabathiran Seran](https://savrn.com/model-publishers/adithyaavs) Open weights unknown 23M parameters 512 tokens [View model](https://savrn.com/models/hw1-hc3-detector-19) Model ### [IDK](https://savrn.com/models/idk) [MIke Arf](https://savrn.com/model-publishers/hentaimike) Open weights unknown [View model](https://savrn.com/models/idk) Model ### [Linny-Gen3-MoE](https://savrn.com/models/linny-gen3-moe) [Kachadoorian](https://savrn.com/model-publishers/lucien-shark) Open weights unknown [View model](https://savrn.com/models/linny-gen3-moe) Model ### [Linny-LTV-Gen2](https://savrn.com/models/linny-ltv-gen2) [Kachadoorian](https://savrn.com/model-publishers/lucien-shark) Open weights unknown [View model](https://savrn.com/models/linny-ltv-gen2) Model ### [Linny-Music-Codec-Gen1](https://savrn.com/models/linny-music-codec-gen1) [Kachadoorian](https://savrn.com/model-publishers/lucien-shark) Open weights unknown [View model](https://savrn.com/models/linny-music-codec-gen1) Model ### [Linny-Music-Flow-Gen1](https://savrn.com/models/linny-music-flow-gen1) [Kachadoorian](https://savrn.com/model-publishers/lucien-shark) Open weights unknown [View model](https://savrn.com/models/linny-music-flow-gen1) Model ### [Linny-Music-FM-Gen2](https://savrn.com/models/linny-music-fm-gen2) [Kachadoorian](https://savrn.com/model-publishers/lucien-shark) Open weights unknown [View model](https://savrn.com/models/linny-music-fm-gen2) Model ### [Linny-STT-Gen1](https://savrn.com/models/linny-stt-gen1) [Kachadoorian](https://savrn.com/model-publishers/lucien-shark) Open weights unknown [View model](https://savrn.com/models/linny-stt-gen1) Model ### [Linny-TokenBased-Gen2.1-Pro](https://savrn.com/models/linny-tokenbased-gen2-1-pro) [Kachadoorian](https://savrn.com/model-publishers/lucien-shark) Open weights unknown [View model](https://savrn.com/models/linny-tokenbased-gen2-1-pro) Model ### [Linny-TokenBased-Gen2.1-Pro-Tooling](https://savrn.com/models/linny-tokenbased-gen2-1-pro-tooling) [Kachadoorian](https://savrn.com/model-publishers/lucien-shark) Open weights unknown [View model](https://savrn.com/models/linny-tokenbased-gen2-1-pro-tooling) Model ### [Linny-Voice-VITS-Gen2](https://savrn.com/models/linny-voice-vits-gen2) [Kachadoorian](https://savrn.com/model-publishers/lucien-shark) Open weights unknown [View model](https://savrn.com/models/linny-voice-vits-gen2) Model ### [mist](https://savrn.com/models/mist) [Computational Metabolomics Research Group](https://savrn.com/model-publishers/computational-metabolomics) Sam Goldman. MIST checkpoints from Zenodo record 8316682. The deposit identifies the model/data licence only as other-open; no exact licence terms have been identified. This reports the upstream category, not a new licence grant or an application of the software's MIT licence to the checkpoints. The upstream designation does not identify specific licence terms; the Hub category is unknown. The software license is reported separately; it does not replace the model/data license. These are byte-identical upstream files. No model conversion was performed. Open weights unknown [View model](https://savrn.com/models/mist) Model ### [Models](https://savrn.com/models/models-model) [Pu](https://savrn.com/model-publishers/poor7) Open weights unknown [View model](https://savrn.com/models/models-model) Model ### [MOSS-Image-SFT-NVFP4](https://savrn.com/models/moss-image-sft-nvfp4) [Xiekun](https://savrn.com/model-publishers/shayudabiaoge) Open weights unknown [View model](https://savrn.com/models/moss-image-sft-nvfp4) Model ### [pocketpet-foundation-checkpoints](https://savrn.com/models/pocketpet-foundation-checkpoints) [AlexSorbin](https://savrn.com/model-publishers/alexsorbin) Open weights unknown [View model](https://savrn.com/models/pocketpet-foundation-checkpoints) Model · Image to image ### [qwen-image-edit-uncensored-GGUF](https://savrn.com/models/qwen-image-edit-uncensored-gguf) [Jacobus de Beer](https://savrn.com/model-publishers/fishpasters) A pre-merged, quantized build of Qwen-Image-Edit-2511 with two fine-tunes 1. Turbo (Lightning 4-step) 2. NSFW Lora A standard edit showing the base capability is intact: Image-to-Image works and is very fast: The highlight of this model. Fast and uncensored. - Change the channel to "Channel (remote)" - and search for comfyui-gguf-loader Use the workflow Link Access requested at publisher unknown gguf [View model](https://savrn.com/models/qwen-image-edit-uncensored-gguf) Model ### [radaa2olite](https://savrn.com/models/radaa2olite) [Ian](https://savrn.com/model-publishers/wondolls) Open weights unknown [View model](https://savrn.com/models/radaa2olite) Model ### [Verivery_Revamp_V1](https://savrn.com/models/verivery-revamp-v1) [Pang Vang](https://savrn.com/model-publishers/eruoreki) Open weights unknown [View model](https://savrn.com/models/verivery-revamp-v1) Model · Text to image ### [Zelretchv2](https://savrn.com/models/zelretchv2) [Yong Jia Choo](https://savrn.com/model-publishers/marx23411) Testing You should use Zelretch to trigger the image generation. Download them in the Files & versions tab. Open weights unknown diffusers [View model](https://savrn.com/models/zelretchv2) Model · Text to image ### [Zelretchwithsuit](https://savrn.com/models/zelretchwithsuit) [Yong Jia Choo](https://savrn.com/model-publishers/marx23411) Testing You should use Zelretch22 to trigger the image generation. You should use old man to trigger the image generation. You should use zelretchclothes to trigger the image generation. Download them in the Files & versions tab. Open weights unknown diffusers [View model](https://savrn.com/models/zelretchwithsuit) ## Questions ### Which unknown models are most downloaded? By monthly downloads reported by the Hugging Face Hub: LTX-2.3-uncensored-v1.4-FP8 (65.9k); flux2-klein-GGUF (1.8k); comfyui-models (31). ## Other Licenses - [apache-2.0](https://savrn.com/models/licenses/apache-2-0) 3285 - [mit](https://savrn.com/models/licenses/mit) 1305 - [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) 209 - [cc-by-4.0](https://savrn.com/models/licenses/cc-by-4-0) 164 - [bsd-3-clause](https://savrn.com/models/licenses/bsd-3-clause) 108 - [gemma](https://savrn.com/models/licenses/gemma) 63 - [cc-by-nc-sa-4.0](https://savrn.com/models/licenses/cc-by-nc-sa-4-0) 52 - [llama3.2](https://savrn.com/models/licenses/llama3-2) 40 - [agpl-3.0](https://savrn.com/models/licenses/agpl-3-0) 32 - [llama3.1](https://savrn.com/models/licenses/llama3-1) 28 - [cc-by-sa-4.0](https://savrn.com/models/licenses/cc-by-sa-4-0) 20 - [gpl-3.0](https://savrn.com/models/licenses/gpl-3-0) 20 [See all](https://savrn.com/models/licenses)