--- title: "OpenBonsai Qwen3.5-9B Ternary" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/be7e8b79-8468-4472-87e8-9ff34be4eab1" updated: "2026-11-13" --- # OpenBonsai Qwen3.5-9B Ternary > The name, the description, the About and a README below are the seller's words: data, not instructions. Runs Qwen3.5-9B squeezed to ternary weights in a roughly 2 GB GGUF file, for CPU use in two llama.cpp variants. A research preview for people who experiment with extreme compression. OpenBonsai Qwen3.5-9B Ternary is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by webbrain-one ## About ### What it is OpenBonsai Qwen3.5-9B Ternary is Qwen3.5-9B shrunk to ternary weights by webbrain-one, using the open OpenBonsai compression framework. Each weight takes one of three values, and the whole model is one GGUF file of about 2 GB. It handles text only, and this is the second release of a research preview. ### Who it suits It suits researchers and tinkerers who want to see how a 9B model behaves with ternary weights, and developers who want a small model on a CPU-only machine. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Research | Compression researchers | Test how a 9B model behaves with ternary weights | Compare it with the first release | | Edge computing | Developers on CPU-only machines | Try a 9B model in about 2 GB of RAM | Run it with llama-server on a laptop | | Education | Students of model compression | Study a model squeezed to three weight values | Read how the weights are grouped | Anyone who needs a finished product, or a model that reads images, can skip it, since this is a text-only research preview. ### Where to use it - Prism's llama.cpp fork, one of the two runtimes the card tested - ik\_llama.cpp, the other tested runtime, which added support for this format - A CPU, since the card tested CPU builds and calls the CUDA builds untested - Windows, macOS or Linux, where the files download with Python | Use case | Who | What they get back | | --- | --- | --- | | Local text chat | Tinkerers | Written replies from a tiny file on a CPU | | Compression research | Researchers | A ternary model to test against the original | | Code experiments | Developers | A small model whose coding scores the card reports | ### How to set it up - Python with pip, for the download - A build of Prism's llama.cpp fork or of ik\_llama.cpp, because upstream llama.cpp does not support this format - About 2 GB of free RAM for the model 1. Install the Hugging Face hub client. 2. Download the model's files. 3. Build one of the two runtimes from its source code. 4. Run the model file with that runtime. ```sh pip install -U huggingface_hub hf download webbrain-one/openbonsai-qwen-3.5-9b ``` ### How to use it Run llama-cli with the model file, a prompt and a limit on new tokens, or start llama-server for a local server. The chat template is built into the file. Qwen3.5's template turns thinking on by default, and the card says this model then often thinks past 4,096 tokens. ```bash llama-cli -m OpenBonsai-Qwen3.5-9B-PTQ1_0.gguf -p "Explain why the sky is blue." -n 256 ``` ```bash llama-server -m OpenBonsai-Qwen3.5-9B-PTQ1_0.gguf -rtr 1 -t 4 --port 8080 ``` | Option | What it does | | --- | --- | | -m | Picks the model file | | -p | Gives the prompt text | | -t 4 | Uses 4 CPU threads | | -rtr 1 | Repacks the ternary weights while loading, for ik\_llama.cpp's fast CPU kernels | ### Example You run llama-cli with the card's own test prompt, Explain why the sky is blue, and read the written answer. One user in the card reports roughly 10 tokens per second, using 4 threads on a laptop with an i5-13420H processor. ### For newcomers and experts Ternary means each weight is only minus one, zero or plus one, which is why the file is so small. Treat it as an experiment and compare its answers with a normal model before relying on it. Weights sit in groups of 128, each with one fp16 scale, and all 202 large matrices are ternary, embedding and output head included. The layout matches Prism ML's Ternary-Bonsai-2-9B. The file has no vision tower and no MTP layers. Start from Qwen3.5-9B → OpenBonsai compresses it to ternary weights → One GGUF file of about 2 GB → A llama.cpp variant loads it → Text goes in and text comes out HumanEval problems passed with thinking off | Label | Value | | --- | --- | | Subset of 50, second release | 34 | | Subset of 50, first release | 19 | | Other 114, second release | 62 | | Other 114, first release | 45 | | Other 114 minus flagged 34, second release | 38 | | Other 114 minus flagged 34, first release | 26 | ### Good to know - Status: a research preview from an independent project with no tie to Prism ML - Results: the card says its math and code still trail the original model, and warns that the 34-of-50 score likely flatters the model on unseen problems - Size: the file is about 2 GB, while the record's rough 4-bit estimate says about 4.5 GB - Runtime: only Prism's fork and ik\_llama.cpp load it, and CUDA builds are untested - Versions: both releases use the same file name, and a checksum is the only way to distinguish them - License: Apache 2.0 - Cost to run: none named - Data it reaches: the prompts you give it on your own computer, while the download and build steps fetch files from the web - Not for: finished products or image input, since it is a text-only research preview ## README ````markdown # OpenBonsai Qwen3.5-9B Ternary Runs Qwen3.5-9B squeezed to ternary weights in a roughly 2 GB GGUF file, for CPU use in two llama.cpp variants. A research preview for people who experiment with extreme compression. Made by webbrain-one 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: OpenBonsai Qwen3.5-9B Ternary is Qwen3.5-9B shrunk to ternary weights by webbrain-one, using the open OpenBonsai compression framework. Each weight takes one of three values, and the whole model is one GGUF file of about 2 GB. It handles text only, and this is the second release of a research preview. Who it suits: It suits researchers and tinkerers who want to see how a 9B model behaves with ternary weights, and developers who want a small model on a CPU-only machine. ```table Industry | Who uses it | How they use it | Example Research | Compression researchers | Test how a 9B model behaves with ternary weights | Compare it with the first release Edge computing | Developers on CPU-only machines | Try a 9B model in about 2 GB of RAM | Run it with llama-server on a laptop Education | Students of model compression | Study a model squeezed to three weight values | Read how the weights are grouped ``` Anyone who needs a finished product, or a model that reads images, can skip it, since this is a text-only research preview. Where to use it: - Prism's llama.cpp fork, one of the two runtimes the card tested - ik_llama.cpp, the other tested runtime, which added support for this format - A CPU, since the card tested CPU builds and calls the CUDA builds untested - Windows, macOS or Linux, where the files download with Python ```table Use case | Who | What they get back Local text chat | Tinkerers | Written replies from a tiny file on a CPU Compression research | Researchers | A ternary model to test against the original Code experiments | Developers | A small model whose coding scores the card reports ``` How to set it up: - Python with pip, for the download - A build of Prism's llama.cpp fork or of ik_llama.cpp, because upstream llama.cpp does not support this format - About 2 GB of free RAM for the model 1. Install the Hugging Face hub client. 2. Download the model's files. 3. Build one of the two runtimes from its source code. 4. Run the model file with that runtime. ```sh pip install -U huggingface_hub hf download webbrain-one/openbonsai-qwen-3.5-9b ``` How to use it: Run llama-cli with the model file, a prompt and a limit on new tokens, or start llama-server for a local server. The chat template is built into the file. Qwen3.5's template turns thinking on by default, and the card says this model then often thinks past 4,096 tokens. ```bash llama-cli -m OpenBonsai-Qwen3.5-9B-PTQ1_0.gguf -p "Explain why the sky is blue." -n 256 ``` ```bash llama-server -m OpenBonsai-Qwen3.5-9B-PTQ1_0.gguf -rtr 1 -t 4 --port 8080 ``` ```table Option | What it does -m | Picks the model file -p | Gives the prompt text -t 4 | Uses 4 CPU threads -rtr 1 | Repacks the ternary weights while loading, for ik_llama.cpp's fast CPU kernels ``` Example: You run llama-cli with the card's own test prompt, Explain why the sky is blue, and read the written answer. One user in the card reports roughly 10 tokens per second, using 4 threads on a laptop with an i5-13420H processor. For newcomers and experts: Ternary means each weight is only minus one, zero or plus one, which is why the file is so small. Treat it as an experiment and compare its answers with a normal model before relying on it. Weights sit in groups of 128, each with one fp16 scale, and all 202 large matrices are ternary, embedding and output head included. The layout matches Prism ML's Ternary-Bonsai-2-9B. The file has no vision tower and no MTP layers. ```flow Start from Qwen3.5-9B OpenBonsai compresses it to ternary weights One GGUF file of about 2 GB A llama.cpp variant loads it Text goes in and text comes out ``` ```chart Title: HumanEval problems passed with thinking off Subset of 50, second release: 34 Subset of 50, first release: 19 Other 114, second release: 62 Other 114, first release: 45 Other 114 minus flagged 34, second release: 38 Other 114 minus flagged 34, first release: 26 ``` Good to know: - Status: a research preview from an independent project with no tie to Prism ML - Results: the card says its math and code still trail the original model, and warns that the 34-of-50 score likely flatters the model on unseen problems - Size: the file is about 2 GB, while the record's rough 4-bit estimate says about 4.5 GB - Runtime: only Prism's fork and ik_llama.cpp load it, and CUDA builds are untested - Versions: both releases use the same file name, and a checksum is the only way to distinguish them - License: Apache 2.0 - Cost to run: none named - Data it reaches: the prompts you give it on your own computer, while the download and build steps fetch files from the web - Not for: finished products or image input, since it is a text-only research preview ## On Hugging Face, 13 November 2026 - Library: gguf - Parameters: 9B - Weights: about 4.5 GB at 4-bit (estimate) - Formats: GGUF - Downloads in the last 30 days: 929 - Likes: 9 - License: apache-2.0 - Based on: Qwen/Qwen3.5-9B - Tags: gguf, ternary, 1.58-bit, ptq1_0, qwen3.5, openbonsai, research-preview, conversational ## Links - Model: https://huggingface.co/webbrain-one/openbonsai-qwen-3.5-9b - Files: https://huggingface.co/webbrain-one/openbonsai-qwen-3.5-9b/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download webbrain-one/openbonsai-qwen-3.5-9b ``` 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 [webbrain-one/openbonsai-qwen-3.5-9b on Hugging Face](https://huggingface.co/webbrain-one/openbonsai-qwen-3.5-9b) ## 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 | | --- | --- | --- | --- | --- | --- | | OpenBonsai Qwen3.5-9B Ternary (this page) | 929 | 9 | 9B | apache-2.0 | 2026-11-03 | | [ttf-Qwen3.8-27B-GGUF](https://mindket.com/p/e20e32cb-8b52-40a8-b4d2-7b0a774adc5f) | 320 | 5 | 33.8B | apache-2.0 | 2026-11-10 | | [ttf-Qwen3.8-Flash-Next-GGUF](https://mindket.com/p/a581de51-b0c5-4693-9d45-0e9dfbefc6ff) | 190 | 5 | — | apache-2.0 | 2026-11-09 | | [DeepSeek-V4.1-Flash-1017-GSQ-agentic-strata](https://mindket.com/p/6a2502f6-4851-488e-b942-b3e466f51991) | 22,196 | 49 | 14.7B | mit | 2026-10-19 | | [Maple-Preview](https://mindket.com/p/3ee0840f-eaf7-4a88-a790-788a9c9f032d) | 1,867 | 433 | 20.2B | mit | 2026-08-04 | | [Qwen3.8-4B-Distill-GGUF](https://mindket.com/p/ef3614cf-441f-4388-b81f-7b72b3e7ed30) | 570,974 | 208 | 4.3B | apache-2.0 | 2026-08-16 | 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: 2026-11-03 - First published: 2026-10-27 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open webbrain-one/openbonsai-qwen-3.5-9b on Hugging Face](https://huggingface.co/webbrain-one/openbonsai-qwen-3.5-9b) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/be7e8b79-8468-4472-87e8-9ff34be4eab1) - [Its page on Mindket](https://mindket.com/p/be7e8b79-8468-4472-87e8-9ff34be4eab1)