# sovereign-anthology-gemma-2-2b by Adeilson Costa: Open Model Source: https://savrn.com/models/sovereign-anthology-gemma-2-2b Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve sovereign-anthology-gemma-2-2b (3.2B 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 | 6.4 GB | 7.7 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 | 3.2 GB | 3.8 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 | 1.6 GB | 1.9 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. [sovereign-anthology-gemma-2-2b on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/sovereign-anthology-gemma-2-2b/gpus) ## Model Card Most language models today act as polite chatbots: they offer conversational summaries, generic advice, and surface-level bullet points. But when the stakes are existential — when critical production services fail, corporate partnerships fracture, infrastructure is compromised, or you are facing high-consequence decisions under severe uncertainty — you don't need a conversational chatbot. You need a dedicated Directorate of Intelligence on your team. What if you could run an autonomous operational intelligence analyst directly on your local workstation — 100% private, offline, and air-gapped? That is the genesis of Sovereign Gotham / Sovereign Anthology. Rather than feeding an AI thousands… Excerpt from the card by Adeilson Costa, licensed gemma. ## Configuration Architecture Gemma2ForCausalLM Context length (tokens) 8,192 Layers 26 Hidden size 2,304 Feed-forward size 9,216 Attention heads 8 Key/value heads 4 Head dimension 256 Vocabulary size 256,000 Sliding window (tokens) 4,096 RoPE base 10000 Stored precision float16 Model type gemma2 ## Identity and Version Repository KolmogorovAcc/sovereign-anthology-gemma-2-2b Publisher Adeilson Costa Task Text generation Modality Text Library transformers Parameters 3.2B parameters Languages en Revision a05d9d1d7935974dce7c9d43567750cb648195c1 First published 2026-09-20 Last updated 2026-09-22 ## Files and Weights 17 files, 20.3 GB in total. The weights are 6 files totalling 20.3 GB in gguf, safetensors. Weights6 files · 20.3 GB Configuration4 files · 26.5 KB Tokenizer3 files · 38.7 MB Documentation1 file · 28.9 KB Other2 files · 684 B Repository1 file · 1.9 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00002.safetensors | Weights | 5.0 GB | d6e47ba037d3 | | model-00002-of-00002.safetensors | Weights | 1.4 GB | 2927526e21b9 | | sovereign_anthology_gemma2_2b.gguf | Weights | 5.2 GB | 454fd53f528f | | sovereign_anthology_gemma2_2b_q4_k_m.gguf | Weights | 1.7 GB | 43f9a77d4bd5 | | sovereign_anthology_gemma2_2b_v2.gguf | Weights | 5.2 GB | 172120fb980e | | sovereign_anthology_gemma2_2b_v2_q4_k_m.gguf | Weights | 1.7 GB | a4866adeb3df | | config.json | Configuration | 996 B | — | | generation_config.json | Configuration | 221 B | — | | model.safetensors.index.json | Configuration | 24.6 KB | — | | special_tokens_map.json | Configuration | 670 B | — | | README.md | Documentation | 28.9 KB | — | | Modelfile | Other | 347 B | — | | Modelfile.q4 | Other | 337 B | — | | .gitattributes | Repository | 1.9 KB | — | | tokenizer.json | Tokenizer | 34.4 MB | 5f7eee611703 | | tokenizer.model | Tokenizer | 4.2 MB | 61a7b147390c | | tokenizer_config.json | Tokenizer | 49.1 KB | — | ## License and Download License gemma Access Open weights, no gate Download size 20.3 GB [Download from Adeilson Costa](https://huggingface.co/KolmogorovAcc/sovereign-anthology-gemma-2-2b) Released by Adeilson Costa through its official repository on Hugging Face. ## Built From - Derived from google/gemma-2-2b-it - Quantized from google/gemma-2-2b-it ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 20.3 GB | | 16-bit | 6.4 GB | | 8-bit | 3.2 GB | | 4-bit | 1.6 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About sovereign-anthology-gemma-2-2b ### How much GPU memory does sovereign-anthology-gemma-2-2b need? About 7.7 GB at 16-bit and 1.9 GB at 4-bit: the weights (3.2B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run sovereign-anthology-gemma-2-2b 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. ### Can I use sovereign-anthology-gemma-2-2b commercially? Yes, with conditions. sovereign-anthology-gemma-2-2b is released under Gemma Terms of Use. Gemma models are released under Google's Gemma Terms of Use, which permit commercial use and redistribution subject to the Gemma Prohibited Use Policy, whose restrictions must be passed on to anyone the model is distributed to. ### What is sovereign-anthology-gemma-2-2b's context length? 8,192 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [Llama-3.2-3B-Instruct](https://savrn.com/models/llama-3-2-3b-instruct) [Meta Llama](https://savrn.com/model-publishers/meta-llama) The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks. Model Architecture: Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for… Access requested at publisher llama3.2 3.2B parameters transformers [View model](https://savrn.com/models/llama-3-2-3b-instruct) Model · Text generation ### [Llama-3.2-3B-Legal-SFT](https://savrn.com/models/llama-3-2-3b-legal-sft) [Muhammad Idris](https://savrn.com/model-publishers/midris) This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 3.2B parameters 131,072 tokens transformers [View model](https://savrn.com/models/llama-3-2-3b-legal-sft) Model · Text generation ### [Llama-3.2-3B-Instruct-Profesor-Albus-Dumbledore](https://savrn.com/models/llama-3-2-3b-instruct-profesor-albus-dumbledore) [Nicole Rosas](https://savrn.com/model-publishers/rrnicole1014) This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 3.2B parameters 131,072 tokens transformers [View model](https://savrn.com/models/llama-3-2-3b-instruct-profesor-albus-dumbledore) Model · Text generation ### [Llama-3.2-3B-Thai_CRM](https://savrn.com/models/llama-3-2-3b-thai-crm) [Yothin](https://savrn.com/model-publishers/yothins) 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%… Open weights llama3.2 3.2B parameters 131,072 tokens [View model](https://savrn.com/models/llama-3-2-3b-thai-crm) Model · Text generation ### [amharic-bell-tts-4bit](https://savrn.com/models/amharic-bell-tts-4bit) [BmanCman](https://savrn.com/model-publishers/bmancman) This is the model card of a transformers model that has been pushed on the Hub. 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). Open weights 3.3B parameters 131,072 tokens transformers [View model](https://savrn.com/models/amharic-bell-tts-4bit) Model · Text generation ### [Qwen2.5-3B-Instruct](https://savrn.com/models/qwen2-5-3b-instruct) [Qwen](https://savrn.com/model-publishers/qwen) Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and… Open weights other 3.1B parameters 32,768 tokens transformers [View model](https://savrn.com/models/qwen2-5-3b-instruct) ## Adeilson Costa [All models and datasets](https://savrn.com/model-publishers/kolmogorovacc) ## Versions - [a05d9d1d7935](https://savrn.com/models/sovereign-anthology-gemma-2-2b/versions/a05d9d1d7935) · current 2026-09-22 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [All models under gemma](https://savrn.com/models/licenses/gemma) - [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 2026-09-22. - [Hugging Face record](https://huggingface.co/KolmogorovAcc/sovereign-anthology-gemma-2-2b) - [How the hub is built](https://savrn.com/model-hub/methodology)