SAVRN Model Hub
Open-Weight Models
An open-weight model is an AI model whose trained weights are published for anyone to download. The weights are what the model learned in training. With a copy of them you can run the model on hardware you control and train it further on your own data.
Open weights are not the same as open source. Many publishers release the weights without the training data or code, and the license sets what you may do with the model. This library puts each model's full card, architecture, files, license and published evaluations on one page.
12,579Models
3,583Datasets
291Papers
7,578Publishers
12,850Sourced relationships
Updated 2026-10-23 · How the library is built
12,579 models, sorted by most downloaded.
weighted/imatrix quants of https://huggingface.co/SubMaroon/Kitchoon-V2-26B-A4B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Kitchoon-V2-26B-A4B-GGUF This is a vision model - mmproj files (if any) will be in the static repository. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the…
No model weights or adapters are available to download. This repository contains a model card only. It is not a loadable Transformers model. No release date is promised, and no third-party weights have been uploaded. KnowinRouter jointly selects one capability expert and optional knowledge/perception under a bounded acquisition budget. The intended portfolio uses a shared Qwen3-VL-8B backbone and three independent LoRA adapters: General (continued pretraining), Spatial Reasoning, and Spatiotemporal. A frozen Qwen3-VL-2B descriptor feeds the utility router. After one acquisition round, the Packet Verifier retains valid evidence with positive predicted gain while keeping the expert fixed. The…
Kokoro-82M (StyleTTS2 + iSTFTNet) exported to Apple's Core AI.aimodel format for iOS 27 and macOS 26. Built for OpenReader iOS, an on-device document reader. Published because the export differs from the community recipe in one way that matters, and because a working Core AI TTS export was hard enough to arrive at that it is worth not repeating. Three fixed-shape bundles with two host steps between them. Kokoro's acoustic graph has exactly one data-dependent length — the duration-to-alignment expansion L = sum(preddur) — so the model is cut where that length appears rather than being made dynamic. Token bucket 128, frame bucket 512 — one pass renders 12.8 s of audio. Fixed buckets are not a…
This model was converted to MLX format from hexagrad/Kokoro-82M using mlx-audio version 0.0.1. Refer to the original model card for more details on the model.
GGUF quantizations of Aleph-Alpha/Kolibri-1 — trained from scratch, with tool calling, an explicit reasoning mode and a 262 K native context. Apache-2.0. Because only \~3.5 B parameters are active per token, it decodes like a small model while carrying the knowledge capacity of a large one: \~51 tokens/s on a DGX Spark (GB10) at 4.6 bpw. arch kolibri1 78.1 B params, vocab 128,000 layers 50 FFN MoE 384 experts, top-6, +1 shared (ungated); expert ffn 512 routing select top-6 on logits + per-expert bias, weight by sigmoid(logits), no renorm attention 48 heads / 4 KV, headdim 128, per-head q/k RMSNorm 4 sliding-window layers (window 513, RoPE): 1 full-attention layer (no RoPE) context 262,144…
Unofficial GGUF quantization of Aleph Alpha's Kolibri-1. Requires the experimental Kolibri patch for llama.cpp. Get the patched runtime from Eliasfpv28/Kolibri-1-Q3KS-GGUF, and follow Eliasfpv28's build instructions to build the patched llama.cpp. The tested runtime uses base revision edd6e2bbdad5930899a93db8fa73c3b61c7b9bcc. Kolibri-1 is a text model for German and English, with reasoning and tool-calling modes. It has 78.10 billion parameters and activates about 3.46 billion per token. The following llama-bench runs use an RTX Pro 6000 Blackwell Server Edition on RunPod. The Pod has 96 GB VRAM, 188 GB host RAM and 32 allocated vCPUs. Measurements use three repetitions, 16 CPU threads…
Using llama.cpp release b11716 for quantization. Don't know which to choose? Grab Q4KM (49.76GB) - usually a good mix of size and performance. Download instructions available here First, make sure you have the Hugging Face CLI installed: The files marked true in the Split column above are stored as multiple parts in a folder. To download all the parts to a local folder, run: You can either specify a new local-dir (Kolibri-1-Q80) or download them all in place (./) These quants run with llama.cpp - installable in one line via llama.app: llama-server includes a built-in chat web UI, served at http://localhost:8080 by default. These quants were made with llama.cpp release b11716 - if this…
Stable Diffusion 실습 코드입니다. 콘크리트 손상 사진을 소재로, 확산 모델의 원리부터 LoRA 파인튜닝과 ControlNet 조건부 생성까지 다룹니다. 실습은 01T2I → 02CtrlGen → 03Inpaint 순서입니다. 스크립트는 각자의 폴더 안에서 실행하며, 결과 그림은 그 폴더의./outputs/ 에 저장됩니다. 01·02는 공개 이미지와 공개 ControlNet으로 원리만 보고, 03·04에서 DatasetDmg로 직접 학습하고 비교합니다. 자세한 내용은 02CtrlGen/README.md를 보세요. 자세한 내용은 03Inpaint/README.md를 보세요. 실제로 촬영한 사진입니다. DatasetDmg(ControlNet 생성물)와는 출처가 다릅니다. 전부 1024px 원본 그대로입니다. 01T2I의 LoRA 학습은 불러올 때 512로 줄여 쓰고, 02CtrlGen은 1024를 그대로 씁니다 — ControlNet 가중치가 1024로 학습돼서 세 폴더는 파일명이 1:1로 짝을 이룹니다 (000000271image →.png /.png /.txt). 100장 중 2장은 마스크가 전부 검정입니다. 캡션도 "no visible damage"이므로 정상이며, CUDA GPU가 필요합니다. Colab에서는 이 폴더를 통째로 MyDrive/KomapperSDFTPracticeCode 에 올린 뒤, 각 스크립트
Generated using https://oneshotlora.com Users are solely responsible for complying with all applicable local, national, and international laws and regulations when using this model. Do not use it for any unlawful purpose.
I took down the HF Space to avoid any issues due to this: You can either try to find a mirror or make your own HF Space/modify it to run it on Runpod by cloning my Github repo. Uploaded some random LoRAs that I was gonna use later on HF Space. Now for Krea-2.
I took down the HF Space to avoid any issues due to this: You can either try to find a mirror or make your own HF Space/modify it to run it on Runpod by cloning my Github repo. Uploaded some random LoRAs that I was gonna use later on HF Space. Now for Krea-2.
These LoRAs were extracted from fine-tuned checkpoints. I did this primarily for myself because LoRAs are easier to work with: they can be mixed in real time and assigned different weights/strengths. This also saves space on your local computer. They work well at 100–150% strength. Choose a rank according to your taste and your hardware capabilities (the lower the rank, the less memory you need). However, some of my test generations showed that a lower rank can sometimes be preferable: it does not cause artifacts, and the result is closer to the reference image generated using the checkpoint from which the LoRA was extracted. A lot of time, electricity, and compute went into this on my…
Various workflows I found that run Krea2, most of them from Civitai. This is just a backup, all credits to the creators.
Model Collections
Hand-picked starting points, each with the reason it exists.
Collection · 4 entries
Embedding models for retrieval
Sentence and document embedding models used to build retrieval systems. Dimension and sequence length matter more than size here, and both come from the publisher.
Collection · 4 entries
Models that fit on one accelerator
Models whose publisher-reported parameter count puts them within reach of a single accelerator at common precisions. Memory needed depends on precision and serving configuration, so treat the parameter count as the starting point, not the answer.
Collection · 6 entries
Open-weight text models worth knowing
Widely used open-weight language models, chosen because each one is a distinct family rather than a variant of the one above it. Selection, not a ranking.
Collection · 3 entries
Speech and audio models
Recognition and synthesis models, grouped so the two directions are easy to compare.
Open-Weight Models Explained
What is an open-weight model?
An AI model whose trained weights are published for anyone to download, so it can be run, tested and fine-tuned on hardware the user controls.
Is an open-weight model the same as open source?
Not always. Open weights means the trained model can be downloaded. Open source usually also means the training code and data are available and the license allows broad reuse. Many open-weight models release the weights only.
Can I use an open-weight model commercially?
It depends on the license. Apache 2.0 and MIT allow commercial use. Other licenses limit it, for example to non-commercial use or below a set number of users. Every model page here shows its license.
How much memory does an open-weight model need?
About two bytes per parameter at 16-bit precision, so a 7-billion-parameter model needs roughly 14 GB for its weights, plus memory for the context it processes. Each model page lists its parameter count and the size of its files.
Related SAVRN Research
The hub sits beside SAVRN's market data and infrastructure research: what models cost to run, and what it takes to run them.
SAVRN Index
What open models cost to run
The same open-weight model priced by every host that serves it, per million tokens.
Research Hub
Data center trackers and maps
Moratoriums, permits, power, water and capital behind the facilities that run these models.
Method
How the Model Hub is built
Sources, evidence labels, refresh behaviour, and the limits of every comparison here.