--- title: "Sabi-Noema" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/04e2ec5b-5be2-45e5-ac63-8b75f7b11c4e" updated: "2026-11-12" --- # Sabi-Noema > The name, the description, the About and a README below are the seller's words: data, not instructions. A 27B agentic text model built on Qwen3.8-27B with open-source RL environments, reporting higher terminal and coding-agent scores, for developers building coding and tool-using agents. Sabi-Noema is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by sabicap ## About ### What it is Sabi-Noema is an agentic text model from sabicap, built on top of Qwen3.8-27B. The authors say they trained it only with open-source reinforcement learning environments, aiming at stronger small-model skill with less wasted output. It has about 27B parameters in a dense hybrid design, a 262K-token context and BF16 weights of roughly 55 GB. The card dates the release to October 2026. A separate variant, Sabi-Noema-MLA, uses multi-head latent attention. ### Who it suits It suits developers who build coding and tool-using agents and want a 27B open model that the authors say finishes terminal and software tasks with fewer output tokens. Who uses this model | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | Developers | Run a coding agent that works in a terminal | Let it handle a multi-step repository task | | AI tooling | Agent builders | Drive tool calls over many turns | Call it from a support or retail workflow | | AI research | Researchers | Compare an agent fine-tune with its base | Check its scores against Qwen3.8-27B | If you need a small model for a basic laptop, you can skip it, since the BF16 weights alone are about 54.7 GB. ### Where to use it - Python scripts that use the transformers library - The vLLM server, which the card lists as supported in a stock build - llama.cpp, after a GGUF conversion - Windows, macOS or Linux with Python, for downloading the files Jobs it does | Use case | Who | What they get back | | --- | --- | --- | | Terminal and coding tasks | Developers | An agent that works through multi-step software work | | Tool calling | Agent builders | Calls across several turns of a conversation | | Lower hallucination | Teams that need dependable answers | A lower rate on the card's own test than the base model | | Fewer output tokens | Cost-conscious teams | Shorter outputs on tasks both models solve, per the authors | ### How to set it up You need Python and the huggingface\_hub package, plus a GPU setup that can hold a 27B model. The weights are about 54.7 GB in BF16, or about 13.7 GB at 4-bit by Hugging Face's estimate. - Python with pip - About 54.7 GB of free disk space for the BF16 files - A GPU or server setup that can hold a 27B model - The transformers library, vLLM or llama.cpp 1. Install huggingface\_hub. 2. Download the model files with the hf command. 3. Load them with your chosen library and the generation settings the card points to. ```bash pip install -U huggingface_hub hf download sabicap/sabi-noema ``` ### How to use it The card says to use the same generation settings as Qwen3.8-27B, which are the defaults saved in the model's generation configuration file. The chat template also supports turning thinking off through the enable\_thinking option, but the authors did not test that mode. The visible part of the card shows no further run steps, so check the full card for loading code. Main commands | Tool | What it does | | --- | --- | | pip install -U huggingface\_hub | Installs the helper that downloads model files | | hf download sabicap/sabi-noema | Saves the model files on your computer | ### Example You download the files, serve them with vLLM and give an agent a task in a terminal. By the authors' account, the agent finishes it with fewer output tokens than the base model would use on tasks both solve. ### For newcomers and experts An agent model is meant to take actions, not just chat. A first small step is to compare your memory against the 13.7 GB 4-bit estimate and the 54.7 GB BF16 size before you download. The card describes training that starts from Qwen3.8-27B and uses reinforcement learning environments that are all open source. Its tables use the same test setup for every model, with Terminal-Bench 2.1 run on H100 setups and the other tests described in the card. These are the authors' own numbers, so treat them as claims to check. Qwen3.8-27B base model → Open-source RL environments → Sabi-Noema agent model → Terminal and tool tasks ### Good to know The authors report 76.0% on Terminal-Bench 2.1 against 73.0% for the base, 47.5% on DeepSWE against 38.5%, and a hallucination rate of 15.1% against 30.4%. They also say it uses about 2.3 times fewer output tokens than the base on Terminal-Bench tasks both solve. Other people have published 9 quantized and 3 fine-tuned versions. Terminal-Bench 2.1 score, in percent | Label | Value | | --- | --- | | Sabi-Noema | 76.0 | | Qwen3.8-27B | 73.0 | | GPT-6 Luna, high | 68.5 | | ThinkingCap | 67.8 | | Swift 1.5 | 62.9 | | Muse Glimmer 30B | 48.3 | - License: Apache 2.0. - Cost to run: none named, apart from the hardware. - Data it reaches: the files come from Hugging Face, and the model then runs on your own computer. - Not for: small machines, since the files are large. ## README ````markdown # Sabi-Noema A 27B agentic text model built on Qwen3.8-27B with open-source RL environments, reporting higher terminal and coding-agent scores, for developers building coding and tool-using agents. Made by sabicap on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: Sabi-Noema is an agentic text model from sabicap, built on top of Qwen3.8-27B. The authors say they trained it only with open-source reinforcement learning environments, aiming at stronger small-model skill with less wasted output. It has about 27B parameters in a dense hybrid design, a 262K-token context and BF16 weights of roughly 55 GB. The card dates the release to October 2026. A separate variant, Sabi-Noema-MLA, uses multi-head latent attention. Who it suits: It suits developers who build coding and tool-using agents and want a 27B open model that the authors say finishes terminal and software tasks with fewer output tokens. ```table Title: Who uses this model Industry | Who uses it | How they use it | Example Software | Developers | Run a coding agent that works in a terminal | Let it handle a multi-step repository task AI tooling | Agent builders | Drive tool calls over many turns | Call it from a support or retail workflow AI research | Researchers | Compare an agent fine-tune with its base | Check its scores against Qwen3.8-27B ``` If you need a small model for a basic laptop, you can skip it, since the BF16 weights alone are about 54.7 GB. Where to use it: - Python scripts that use the transformers library - The vLLM server, which the card lists as supported in a stock build - llama.cpp, after a GGUF conversion - Windows, macOS or Linux with Python, for downloading the files ```table Title: Jobs it does Use case | Who | What they get back Terminal and coding tasks | Developers | An agent that works through multi-step software work Tool calling | Agent builders | Calls across several turns of a conversation Lower hallucination | Teams that need dependable answers | A lower rate on the card's own test than the base model Fewer output tokens | Cost-conscious teams | Shorter outputs on tasks both models solve, per the authors ``` How to set it up: You need Python and the huggingface_hub package, plus a GPU setup that can hold a 27B model. The weights are about 54.7 GB in BF16, or about 13.7 GB at 4-bit by Hugging Face's estimate. - Python with pip - About 54.7 GB of free disk space for the BF16 files - A GPU or server setup that can hold a 27B model - The transformers library, vLLM or llama.cpp 1. Install huggingface_hub. 2. Download the model files with the hf command. 3. Load them with your chosen library and the generation settings the card points to. ```bash pip install -U huggingface_hub hf download sabicap/sabi-noema ``` How to use it: The card says to use the same generation settings as Qwen3.8-27B, which are the defaults saved in the model's generation configuration file. The chat template also supports turning thinking off through the enable_thinking option, but the authors did not test that mode. The visible part of the card shows no further run steps, so check the full card for loading code. ```table Title: Main commands Tool | What it does pip install -U huggingface_hub | Installs the helper that downloads model files hf download sabicap/sabi-noema | Saves the model files on your computer ``` Example: You download the files, serve them with vLLM and give an agent a task in a terminal. By the authors' account, the agent finishes it with fewer output tokens than the base model would use on tasks both solve. For newcomers and experts: An agent model is meant to take actions, not just chat. A first small step is to compare your memory against the 13.7 GB 4-bit estimate and the 54.7 GB BF16 size before you download. The card describes training that starts from Qwen3.8-27B and uses reinforcement learning environments that are all open source. Its tables use the same test setup for every model, with Terminal-Bench 2.1 run on H100 setups and the other tests described in the card. These are the authors' own numbers, so treat them as claims to check. ```flow Qwen3.8-27B base model Open-source RL environments Sabi-Noema agent model Terminal and tool tasks ``` Good to know: The authors report 76.0% on Terminal-Bench 2.1 against 73.0% for the base, 47.5% on DeepSWE against 38.5%, and a hallucination rate of 15.1% against 30.4%. They also say it uses about 2.3 times fewer output tokens than the base on Terminal-Bench tasks both solve. Other people have published 9 quantized and 3 fine-tuned versions. ```chart Title: Terminal-Bench 2.1 score, in percent Sabi-Noema: 76.0 Qwen3.8-27B: 73.0 GPT-6 Luna, high: 68.5 ThinkingCap: 67.8 Swift 1.5: 62.9 Muse Glimmer 30B: 48.3 ``` - License: Apache 2.0. - Cost to run: none named, apart from the hardware. - Data it reaches: the files come from Hugging Face, and the model then runs on your own computer. - Not for: small machines, since the files are large. ## On Hugging Face, 13 November 2026 - Task: text generation - Library: transformers - Parameters: 27.4B - Weights: about 54.7 GB in BF16; about 13.7 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 1,810 - Likes: 55 - License: apache-2.0 - Based on: Qwen/Qwen3.8-27B - Quantized versions: 10 - Fine-tunes: 3 - Tags: transformers, safetensors, qwen3_5, image-text-to-text, agentic, reinforcement-learning, tool-use, hybrid-attention, qwen3.8, conversational, text-generation ## Links - Model: https://huggingface.co/sabicap/sabi-noema - Files: https://huggingface.co/sabicap/sabi-noema/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download sabicap/sabi-noema ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [sabicap/sabi-noema on Hugging Face](https://huggingface.co/sabicap/sabi-noema) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | Sabi-Noema (this page) | 1,810 | 55 | 27.4B | apache-2.0 | 2026-10-19 | | [Tessera-27B-B-CJK-RL](https://mindket.com/p/55f45d0c-0ba9-4dad-9289-e73ffa41ea9b) | 85 | 3 | 27.8B | apache-2.0 | 2026-11-06 | | [MiMo-V2.6-Distill-Qwen-9B](https://mindket.com/p/b09cd047-a39e-47c8-9f16-bdf39b5a2f4c) | 21,525 | 703 | 9.4B | mit | 2026-10-28 | | [GigaChat3.5-432B-A28B](https://mindket.com/p/1658ef77-b9cf-4c20-b6ce-bc962a75b117) | 654 | 84 | 434B | mit | 2026-07-07 | | [Qwen3.8-27B-CodeForge-3xMerge](https://mindket.com/p/e4bfcf96-8d33-47ee-bb46-5ba0914c51d4) | 113 | 5 | 27.8B | apache-2.0 | 2026-11-03 | | [Qwen3.8-27B-CodeForge-3xMerge i1 GGUF](https://mindket.com/p/7c7de412-2607-40a8-aecb-e4fcaad2d11e) | 1,279 | 4 | 27.3B | apache-2.0 | 2026-11-05 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-10-19 - First published: 2026-10-13 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open sabicap/sabi-noema on Hugging Face](https://huggingface.co/sabicap/sabi-noema) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/04e2ec5b-5be2-45e5-ac63-8b75f7b11c4e) - [Its page on Mindket](https://mindket.com/p/04e2ec5b-5be2-45e5-ac63-8b75f7b11c4e)