# AtmicQuoterv3: Open-Weight Model Source: https://savrn.com/models/atmicquoterv3 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve AtmicQuoterv3 (33M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 7, 2026. [AtmicQuoterv3 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/atmicquoterv3/gpus) ## Model Card Fine-tuned from BAAI/bge-small-en-v1.5 (MultipleNegativesRankingLoss, 3 epochs, batch size 16, lr 2e-5) on the combined AtmicQuoterv1 + AtmicQuoterv3 training data, for exact-citation retrieval over Sri Ramana Maharshi's teachings. Queries are encoded with the BGE query instruction (Represent this sentence for searching relevant passages: ); passages are not. Validation set: 1,006 queries (48 from the root validation.jsonl + 958 from AtmicQuoterv1's validation split). Corpus: 8,742 unique passages (AtmicQuoterv1's corpus and the full citation/RAGcitation.json corpus, after the text normalization described below). "alone" = dense retrieval only, ranking the full corpus. "hybrid BM25" =… Excerpt from the card by Atmic Intelligence Project- Sri Ramanasramam. ## Configuration Architecture BertModel Context length (tokens) 512 Layers 12 Hidden size 384 Feed-forward size 1,536 Attention heads 12 Vocabulary size 30,522 Model type bert ## Identity and Version Repository SriRamanaAtmic/AtmicQuoterv3 Publisher Atmic Intelligence Project- Sri Ramanasramam Task Sentence similarity Modality Text Library sentence-transformers Parameters 33M parameters Languages Not stated by the source Revision 7ef2baa2fa340a2d9793bb6f9479afdeb638dc4a First published 2026-09-13 Last updated 2026-09-28 ## Files and Weights 10 files, 134.2 MB in total. The weights are 1 file totalling 133.5 MB in safetensors. Weights1 file · 133.5 MB Configuration5 files · 1.8 KB Tokenizer2 files · 712.2 KB Documentation1 file · 16.8 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 133.5 MB | 777d09428f82 | | 1_Pooling/config.json | Configuration | 89 B | — | | config.json | Configuration | 790 B | — | | config_sentence_transformers.json | Configuration | 278 B | — | | modules.json | Configuration | 429 B | — | | sentence_bert_config.json | Configuration | 241 B | — | | README.md | Documentation | 16.8 KB | — | | .gitattributes | Repository | 1.5 KB | — | | tokenizer.json | Tokenizer | 711.8 KB | — | | tokenizer_config.json | Tokenizer | 443 B | — | ## License and Download License Not stated by the source Access Open weights, no gate Download size 133.5 MB [Download from Atmic Intelligence Project- Sri Ramanasramam](https://huggingface.co/SriRamanaAtmic/AtmicQuoterv3) Released by Atmic Intelligence Project- Sri Ramanasramam through its official repository on Hugging Face. ## Built From - Derived from [BAAI/bge-small-en-v1.5](https://savrn.com/models/bge-small-en-v1-5) - Described by [arXiv:1807.03748](https://savrn.com/papers/representation-learning-with-contrastive-predictive-coding) - Described by [arXiv:1908.10084](https://savrn.com/papers/sentence-bert-sentence-embeddings-using-siamese-bert-networks) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 133.5 MB | | 16-bit | 0.1 GB | | 8-bit | 0.0 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About AtmicQuoterv3 ### How much GPU memory does AtmicQuoterv3 need? About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (33M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run AtmicQuoterv3 on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### What is AtmicQuoterv3's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Sentence similarity ### [bge-small-vscode-dup](https://savrn.com/models/bge-small-vscode-dup) [Musab Suhail](https://savrn.com/model-publishers/musab6969) This is a sentence-transformers model finetuned from BAAI/bge-small-en-v1.5. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more. First install the Sentence Transformers library: Then you can load this model and run inference. Evaluated with EmbeddingSimilarityEvaluator Approximate statistics based on the first 100 samples: "scale": 20.0, "similarityfct": "cossim", "gatheracrossdevices": false, "directions": [ "querytodoc" "partitionmode": "joint", "hardnessmode": null, "hardnessstrength": 0.0 bibtex title = "Sentence-BERT: Sentence Embeddings using… Open weights 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/bge-small-vscode-dup) Model · Sentence similarity ### [all-MiniLM-L12-v2](https://savrn.com/models/all-minilm-l12-v2) [Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers) This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective. We used the pretrained… Open weights apache-2.0 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/all-minilm-l12-v2) Model · Sentence similarity ### [gte-small](https://savrn.com/models/gte-small) [Dingkun Long](https://savrn.com/model-publishers/thenlper) General Text Embeddings (GTE) model. Towards General Text Embeddings with Multi-stage Contrastive Learning The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large, GTE-base, and GTE-small. The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including information retrieval, semantic textual similarity, text reranking, etc. We compared the performance of the GTE models with other popular text embedding models on the MTEB… Open weights mit 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/gte-small) Model · Sentence similarity ### [e5-small-v2](https://savrn.com/models/e5-small-v2) [Liang Wang](https://savrn.com/model-publishers/intfloat) Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022 This model has 12 layers and the embedding size is 384. Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset. Please refer to our paper at https://arxiv.org/pdf/2212.03533.pdf. Check out unilm/e5 to reproduce evaluation results on the BEIR and MTEB benchmark. Below is an example for usage with sentencetransformers. Package requirements pip install sentencetransformers~=2.2.2 1. Do I need to add the prefix "query: " and "passage: " to input texts? Yes, this is how the model is trained, otherwise you will see a performance degradation.… Open weights mit 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/e5-small-v2) Model · Sentence similarity ### [snowflake-arctic-embed-s](https://savrn.com/models/snowflake-arctic-embed-s) [Snowflake](https://savrn.com/model-publishers/snowflake) 12/04/2024: Release of snowflake-arctic-embed-l-v2.0 and snowflake-arctic-embed-m-v2.0 our newest models with multilingual workloads in mind. These models outperform prior versions of Arctic Embed and we suggest these replace prior versions! 07/26/2024: Release preprint [[2407.18887] Embedding And Clustering Your Data Can Improve Contrastive Pretraining](https://arxiv.org/abs/2407.18887) on arXiv. 07/18/2024: Release of snowflake-arctic-embed-m-v1.5, capable of producing highly compressible embedding vectors that preserve quality even when squished as small as 128 bytes per vector. Details about the development of this model are available in the launch post on the Snowflake engineering… Open weights apache-2.0 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/snowflake-arctic-embed-s) Model · Sentence similarity ### [rubert-tiny2](https://savrn.com/models/rubert-tiny2) [David Dale](https://savrn.com/model-publishers/cointegrated) This is an updated version of cointegrated/rubert-tiny: a small Russian BERT-based encoder with high-quality sentence embeddings. This post in Russian gives more details. The differences from the previous version include: - sentence embeddings approximate LaBSE closer than before; - meaningful segment embeddings (tuned on the NLI task) - the model is focused only on Russian. The model should be used as is to produce sentence embeddings (e.g. for KNN classification of short texts) or fine-tuned for a downstream task. Sentence embeddings can be produced as follows: Alternatively, you can use the model with sentencetransformers: For those who want to run the inference with VLLM, there is a… Open weights mit 29M parameters 2,048 tokens sentence-transformers [View model](https://savrn.com/models/rubert-tiny2) ## Atmic Intelligence Project- Sri Ramanasramam [All models and datasets](https://savrn.com/model-publishers/sriramanaatmic) ## Versions - [7ef2baa2fa34](https://savrn.com/models/atmicquoterv3/versions/7ef2baa2fa34) · current 2026-09-28 ## Explore More - [All sentence similarity models](https://savrn.com/models/tasks/sentence-similarity) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-09-28. - [Hugging Face record](https://huggingface.co/SriRamanaAtmic/AtmicQuoterv3) - [How the hub is built](https://savrn.com/model-hub/methodology)