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.
Updated 2026-10-23 · How the library is built
12,579 models, sorted by most downloaded.
static quants of https://huggingface.co/WasamiKirua/Llama-3.2-3B-Alucard-IT For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. 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…
A DSpark draft model for speculative decoding with unsloth/Llama-3.2-3B-Instruct as the verifier, trained with speculators. The drafter proposes 8 tokens at a time and the verifier checks them in one forward pass, so output is identical to running the verifier alone — a lossless speedup. Mean acceptance length is 3.27 tokens committed per verification step, up to 4.92 on mathreasoning. vLLM loads the verifier automatically from the config — don't pass it separately. Then query the OpenAI-compatible endpoint at http://localhost:8000/v1. 5 Qwen3 layers (hidden size 3072, intermediate size 8192, 24 attention heads over 8 KV heads, sliding-window attention with a 2048-token window), ~0.9B…
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - PEFT 0.21.0
Built with Llama Modelo basado en meta-llama/Llama-3.2-3B-Instruct, ajustado con LoRA para generar consultas SPARQL. Modelo base con el adaptador LoRA: Describe aquí tu dataset, hiperparámetros y métricas. Distribuido bajo la Llama 3.2 Community License. Ver LICENSE y NOTICE. Uso sujeto a la Acceptable Use Policy de Meta.
This repository contains GGUF quantized weights for yothinS/Llama-3.2-3B-ThaiCRM, a model fine-tuned for Customer Relationship Management (CRM) workflows, Thai business communications, and customer behavioral analysis. GGUF files can be run locally on CPU, Apple Silicon, or NVIDIA/AMD GPUs via llama.cpp, Ollama, LM Studio, or carrany/text-generation-webui. Download your chosen GGUF file using the Hugging Face CLI: huggingface-cli download yothinS/Llama-3.2-3B-ThaiCRM-GGUF Llama-3.2-3B-ThaiCRM.Q4KM.gguf --local-dir.
Fine-tuned version of meta-llama/Llama-3.2-3B optimized for Customer Relationship Management (CRM), Customer Behavior Analysis, and Thai business workflows. Trained using Unsloth and Hugging Face's TRL library. from transformers import AutoModelForCausalLM, AutoTokenizer import torch modelid = "yothinS/Llama-3.2-3B-ThaiCRM" tokenizer = AutoTokenizer.frompretrained(modelid) model = AutoModelForCausalLM.frompretrained( modelid, torchdtype=torch.bfloat16, devicemap="auto" messages = [ {"role": "system", "content": "You are a professional CRM and customer behavior specialist."}, {"role": "user", "content": "วิเคราะห์พฤติกรรมลูกค้ารายนี้และแนะนำโปรโมชันรักษาฐานลูกค้า: ยอดซื้อเฉลี่ยลดลง 40%…
This repository provides a ONNX converted and quantized version of meta-llama/Llama-Prompt-Guard-2-22M - Meta LLaMA – Foundation model powering the classifier - Hugging Face Transformers – Model and tokenizer loading - ONNX – Model export and runtime format - ONNX Runtime – Efficient inference backend We use jackhhao/jailbreak-classification for the evaluation (train+test) You can find the full source code, CLI tools, and evaluation scripts in the official GitHub repository.
96 for Qwen and 128 for Llama, compared with 32 for both in v4. Full runs retain 64 prompts, 16 responses per prompt, and 300 total steps. The 24 GB offload profile retains concurrency 8. See the v5 release notes. Higher concurrency has CPU configuration validation only; GPU capacity and throughput have not been measured, and sampled training trajectories may differ. The guided launcher uses majority voting; wrong-label and inverted reward selection are not exposed by this launcher. V5 includes the v4 fix for caches creating a run directory before the launcher. For the standalone v3 cache fix, see the patch notes. Use a separate extraction folder when upgrading. Existing model, checkpoint…
Lodestar-4B is a 4-billion-parameter decision model. You give it a state (plain text, JSON or a long document) and one or more typed questions; it returns a probability for every listed option. Each answer is read from a single forward pass. The model never generates free text, so there is nothing to parse and no output length to budget for. (Probabilities rounded to three decimals.) The same call from Python, run inside the downloaded folder: A score question takes its levels as a list, lowest first, and returns {"type": "score", "score":, "probabilities": {"0": p0, "1": p1,...}}. Every question is rendered into one chat prompt (thinking disabled): The probability of each option is the…
a page (a book, a paper, a report) and it returns structured HTML: headings, paragraphs, tables and formulas marked separately, flowcharts as Mermaid, sheet music as ABC notation. It runs entirely on your own machine. The original GGUF lives under a single personal account, on a single host. If it is renamed, deleted or re-uploaded, people who depend on it lose their download, and access to Hugging Face from mainland China is unreliable. So we keep the original files, unmodified, on ModelScope and on our own Hugging Face account. File names, sizes and sha256 digests all match the original. Reproducible: we also converted and quantized the official Alibaba weights ourselves. The quantized…
[2026.09.18] Released Logics-SWE-Qwen3.6-27B under the Apache-2.0 license. - The technical report is in preparation. A link will be added when available. Logics-SWE-Qwen3.6-27B is a 27B-parameter model developed for repository-level software engineering agents. Starting from the Qwen3.6-27B model used in our study, it combines category-aware expert development with multi-teacher on-policy distillation into a single deployment policy. Repository-level tasks require agents to navigate code, edit files, execute commands, inspect feedback, and iteratively repair their solutions. Our work starts from the category see-saw: aggregate progress during joint RL can conceal opposing changes across…
Longleaf is our local model for coding and agent work: repository edits, debugging, structured tools, and clear answers. Built on Qwen3.6-35B-A3B. - 35B total / 3B active parameters. - MLX 4-bit weights. - 262,144-token configured context. EvalPlus 0.3.1, 164 tasks, pass@1. Thinking off, greedy sampling, 2,048-token output cap, 262,144-token configured context. Generation used our M1 Ultra 231 / 198 / 195 tokens, respectively. CLI sample: five Terminal-Bench 2 tasks on ARM64, thinking off. Per task: 300 seconds, 24 model calls, 32 tool calls, 2,048 output tokens per call. Our M1 Ultra Splash runtime, medium thinking, model already loaded: Read, edit, and test completed in about 6 seconds…
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.