# BAAR6-9M-7 by Isai Lab: Open-Weight Model Source: https://savrn.com/models/baar6-9m-7 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve BAAR6-9M-7 (8M 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 | 0.0 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 | | 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 9, 2026. [BAAR6-9M-7 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/baar6-9m-7/gpus) ## Model Card BAAR5-9M is an ultra-compact multilingual conversational model designed to enable real-time chat under minimal hardware conditions. With just 9 million (9M) parameters, it brings lightweight, interactive dialogue capabilities across 11 languages to extreme resource-constrained environments, embedded devices, and on-device platforms where standard LLMs cannot operate. BAAR5-9M은 최소한의 하드웨어 여건과 극단적인 리소스 제약 환경에서도 11개 언어로 실시간 대화(Chat)가 가능하도록 설계된 900만(9M) 파라미터 규모의 초경량 다국어 언어 모델입니다. 일반적인 대형 모델 구동이 불가능한 초저사양 엣지 및 임베디드 기기에서도 즉각적인 대화형 추론과 초경량 실시간 RAG 시스템 구축을 지원합니다. - Non-Commercial Use Only (비상업적 연구·개인 이용 한정): This model is strictly provided for non-commercial, research, and educational purposes only.… Excerpt from the card by Isai Lab, licensed other. ## Configuration Architecture FHN_T4Max_150M_SingleHead_GAU Context length (tokens) 512 Layers 12 Hidden size 288 Attention heads 1 Vocabulary size 2,048 Stored precision float16 Model type fhn_concept_gau ## Identity and Version Repository aixk/BAAR6-9M-7 Publisher Isai Lab Task Text generation Modality Text Library Not stated by the source Parameters 8M parameters Languages ko, en, ja, zh, es, pt, de, ru Revision 188e5d7b40195b4973e030a9f1f695e4c13a3bdb First published 2026-10-04 Last updated 2026-10-09 ## Files and Weights 13 files, 216.5 MB in total. The weights are 3 files totalling 203.7 MB in pt, safetensors. Weights3 files · 203.7 MB Configuration3 files · 929 B Tokenizer3 files · 551.2 KB Documentation1 file · 6.4 KB Other2 files · 12.2 MB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | checkpoint_step_493000.pt | Weights | 93.7 MB | fe0c4536d46b | | checkpoint_step_494000.pt | Weights | 93.7 MB | 8b8ede509653 | | model.safetensors | Weights | 16.4 MB | 86302d5a86a4 | | baar3_manifest.json | Configuration | 438 B | — | | config.json | Configuration | 393 B | — | | special_tokens_map.json | Configuration | 98 B | — | | README.md | Documentation | 6.4 KB | — | | model_int4_wasm.baar3 | Other | 4.2 MB | 64294bb510ca | | model_int8_wasm.baar3 | Other | 7.9 MB | 118c3349f6e9 | | .gitattributes | Repository | 1.6 KB | — | | tokenizer.json | Tokenizer | 42.2 KB | — | | tokenizer_config.json | Tokenizer | 146 B | — | | tokenizer_state.json | Tokenizer | 508.8 KB | — | ## License and Download License other Access Open weights, no gate Download size 203.7 MB [Download from Isai Lab](https://huggingface.co/aixk/BAAR6-9M-7) Released by Isai Lab through its official repository on Hugging Face. ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 203.7 MB | | 16-bit | 0.0 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 BAAR6-9M-7 ### How much GPU memory does BAAR6-9M-7 need? About 0 GB at 16-bit and 0 GB at 4-bit: the weights (8M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run BAAR6-9M-7 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 license is BAAR6-9M-7 released under? other, as its publisher declares it. Read the license text before commercial use. ### What is BAAR6-9M-7's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [ldt-10m](https://savrn.com/models/ldt-10m) [Compactbot](https://savrn.com/model-publishers/compactbot) A 10,284,480-parameter LLaMA-style text model, trained from scratch. This is a verified first checkpoint for the LDT-10M request (model-requests #12, DedeProGames) — real weights, real training, but undertrained (see the honest status below). It is not a quality release yet; the card states that plainly. Standard LLaMA block, no sliding window, no GQA: The parameter count is the learnable total: the raw safetensors sum is 14,216,640, which double-counts the tied embedding (tok.weight 12288×320 = 3,932,160) that head.weight aliases. Tied, the true count is 10,284,480. - Trained from scratch (no base model). The model learned real context — val loss 4.602 is well below the 7.38 unigram floor… Open weights mit 10M parameters 512 tokens transformers [View model](https://savrn.com/models/ldt-10m) Model · Text generation ### [nanogpt-shakespeare-char](https://savrn.com/models/nanogpt-shakespeare-char) [Ricardo Jose Dos Santos Cruz](https://savrn.com/model-publishers/ricardojscruz1963) 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 11M parameters transformers [View model](https://savrn.com/models/nanogpt-shakespeare-char) Model · Text generation ### [nanoBeard-sloop-14M](https://savrn.com/models/nanobeard-sloop-14m) [Lo Jahn](https://savrn.com/model-publishers/ihatetomatoes) A tiny pirate-themed GPT trained from scratch on a piratized version of TinyStories, then SFT-tuned. Built as a learning project — closer to nanoGPT than to a production LM. - model.safetensors — model weights. - config.json — architecture config (load into training.config.Config). - piratebpe.json — tokenizer (load with tokenizers.Tokenizer.fromfile). - trainingmetadata.json — full training config + metrics snapshot. - banner.png — the banner above. This model is not a transformers model — it uses the custom GPT class from this repo. - Trained on a small synthetic corpus (TinyStories, piratized). Vocabulary, grammar, and world knowledge are extremely narrow. - Short context window (256… Open weights 14M parameters pytorch [View model](https://savrn.com/models/nanobeard-sloop-14m) Model · Text generation ### [hypa-tiny-keys](https://savrn.com/models/hypa-tiny-keys) [Hypa-Intelligence](https://savrn.com/model-publishers/hypaai) 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 15M parameters 512 tokens transformers [View model](https://savrn.com/models/hypa-tiny-keys) Model · Text generation ### [Ornith-1.0-9B](https://savrn.com/models/ornith-1-0-9b) [Ornith](https://savrn.com/model-publishers/ornith-ai) Aloha! Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment. Ornith-1.0-9B is a dense ~9B model (≈19 GB in bf16), so it serves comfortably on a single 80GB GPU. The recipes below stand up an OpenAI-compatible server; add --tensor-parallel-size / --tp if you want to shard across more GPUs. For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-9B requires… Open weights mit 1M parameters 262,144 tokens transformers [View model](https://savrn.com/models/ornith-1-0-9b) Model · Text generation ### [waldito-smoke-v1-r0002-u1-mdagosta-b](https://savrn.com/models/waldito-smoke-v1-r0002-u1-mdagosta-b) [Michael D'Agosta](https://savrn.com/model-publishers/mdagosta) This package uses the standard Transformers Llama causal-language-model architecture with OpenWALDO's schema-1 byte tokenizer. Load the tokenizer with trustremotecode=True. BOM.json inventories every release file and EU-BOM.json contains the EU GPAI training-content disclosure mapping. Open weights 820,736 parameters 512 tokens transformers [View model](https://savrn.com/models/waldito-smoke-v1-r0002-u1-mdagosta-b) ## Isai Lab [All models and datasets](https://savrn.com/model-publishers/aixk) ## Versions - [188e5d7b4019](https://savrn.com/models/baar6-9m-7/versions/188e5d7b4019) · current 2026-10-09 - [a82eed77282b](https://savrn.com/models/baar6-9m-7/versions/a82eed77282b) 2026-10-06 - [ae3fa8a400b9](https://savrn.com/models/baar6-9m-7/versions/ae3fa8a400b9) 2026-10-05 - [9ba07e3e0a05](https://savrn.com/models/baar6-9m-7/versions/9ba07e3e0a05) 2026-10-04 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [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 2026-10-09. - [Hugging Face record](https://huggingface.co/aixk/BAAR6-9M-7) - [How the hub is built](https://savrn.com/model-hub/methodology)