--- title: "Tev-320B" kind: "Kit" category: "Research" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/63d40f1b-6af8-4909-9c96-9f1862166e30" updated: "2026-11-13" --- # Tev-320B > The name, the description, the About and a README below are the seller's words: data, not instructions. A 320B mixture-of-experts agent model that works through long terminal tasks with a single bash tool. Trained with reinforcement learning on 1,170 environments, for researchers under a non-commercial license. Tev-320B is a kit in the Research 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 gordonhu ## About ### What it is Tev-320B is an agent model for long terminal tasks. It starts from GLM-5.3-Flash, a mixture-of-experts model with 320B total and 18B active parameters. It was trained with reinforcement learning on 1,170 verified environments that grade every step, not only the final result. ### Who it suits It suits researchers who study terminal agents and long-horizon tasks, and teams that can host a huge model. The license is non-commercial. Who runs it | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Research | Agent researchers | Study reinforcement learning with progress rewards | Compare Tev-320B with its GLM base | | Software | Teams testing coding agents | Run an agent that works only through bash | Repair a broken build in a container | | Evaluation | Benchmark teams | Run terminal tasks and score pass rates | Score it on Terminal-Bench subsets | If you need a small model or a commercial product, you can skip it. ### Where to use it - The transformers library, on Windows, macOS or Linux with Python - Terminal agent frameworks that give the model one bash tool in a container - Multi-GPU servers, since the weights are about 643 GB in BF16 Jobs it does | Use case | Who | What they get back | | --- | --- | --- | | Long terminal tasks | Agent builders | Step-by-step bash work toward a goal | | Environment repair | Researchers | A workspace fixed turn by turn | | Benchmark runs | Evaluators | Pass rates on Terminal-Bench subsets | ### How to set it up - Python on Windows, macOS or Linux - Large storage and multi-GPU memory, since the files are 49 safetensors shards of about 643 GB - An agent setup that hands the model one bash tool inside a container made for each task 1. Install the Hugging Face Hub tools. 2. Download the model files. 3. Load the model in your agent framework and give it the bash tool. ```sh pip install -U huggingface_hub hf download gordonhu/Tev-320B ``` ### How to use it Run the model as an agent. It receives a terminal task in a container and answers with bash commands, turn by turn. The card describes this one-tool setting but shows no run commands. ```sh hf download gordonhu/Tev-320B ``` ### Example You place the agent in a container that holds a broken data pipeline and ask it to fix the pipeline. It works through bash commands one turn at a time and its workspace gets closer to the expected state. The card does not show a sample session. ### For newcomers and experts If you are new, this is an AI that works at a command line, running commands and reading the results until a task is done. The first small thing to try is reading the card's description of how Tev trains its agents. If you know the field, training uses a latent world, a hidden correct specification that grades both the final answer and every step. The reward adds 0.25 times a progress score to a pass or fail check. The trade-off is evidence: results come from the author's own subsets of Terminal-Bench, with 22 tasks in the 3.0 set and 18 in the 4.0 set. Build a task from a hidden correct world → Corrupt the inputs with repairable defects → The agent works in a container with bash → Score each turn by progress, then the result ### Good to know Terminal-Bench 4.0 CM subset, Pass@1 | Label | Value | | --- | --- | | Claude Opus 5 | 0.52 Pass@1 | | Claude Fable 5 | 0.46 Pass@1 | | GPT-5.6 (sol) | 0.39 Pass@1 | | Tev-320B | 0.37 Pass@1 | | Grok 4.6 | 0.31 Pass@1 | | GLM-5.3-Flash | 0.29 Pass@1 | | Claude Opus 4.8 | 0.27 Pass@1 | | Claude Sonnet 5 | 0.19 Pass@1 | - Gain over its base: Pass@1 is 0.27 against 0.20 on the 3.0 subset, and 0.37 against 0.29 on the 4.0 subset. - Domains: Tev-Gym covers seven domains, from software engineering to quantum computing. - Weights: the files carry the base model's vision encoder untouched. Training and tests used text only, and no MTP weights ship with it. - License: cc-by-nc-4.0, so it is non-commercial. - Cost to run: no API key or paid service is named, but the model needs a huge amount of GPU memory. - Data it reaches: the agent runs bash in a container, so what it can reach depends on how you set that container up. - Not for: commercial use, which the license bars. ## README ````markdown # Tev-320B A 320B mixture-of-experts agent model that works through long terminal tasks with a single bash tool. Trained with reinforcement learning on 1,170 environments, for researchers under a non-commercial license. Made by gordonhu 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: Tev-320B is an agent model for long terminal tasks. It starts from GLM-5.3-Flash, a mixture-of-experts model with 320B total and 18B active parameters. It was trained with reinforcement learning on 1,170 verified environments that grade every step, not only the final result. Who it suits: It suits researchers who study terminal agents and long-horizon tasks, and teams that can host a huge model. The license is non-commercial. ```table Title: Who runs it Industry | Who uses it | How they use it | Example Research | Agent researchers | Study reinforcement learning with progress rewards | Compare Tev-320B with its GLM base Software | Teams testing coding agents | Run an agent that works only through bash | Repair a broken build in a container Evaluation | Benchmark teams | Run terminal tasks and score pass rates | Score it on Terminal-Bench subsets ``` If you need a small model or a commercial product, you can skip it. Where to use it: - The transformers library, on Windows, macOS or Linux with Python - Terminal agent frameworks that give the model one bash tool in a container - Multi-GPU servers, since the weights are about 643 GB in BF16 ```table Title: Jobs it does Use case | Who | What they get back Long terminal tasks | Agent builders | Step-by-step bash work toward a goal Environment repair | Researchers | A workspace fixed turn by turn Benchmark runs | Evaluators | Pass rates on Terminal-Bench subsets ``` How to set it up: - Python on Windows, macOS or Linux - Large storage and multi-GPU memory, since the files are 49 safetensors shards of about 643 GB - An agent setup that hands the model one bash tool inside a container made for each task 1. Install the Hugging Face Hub tools. 2. Download the model files. 3. Load the model in your agent framework and give it the bash tool. ```sh pip install -U huggingface_hub hf download gordonhu/Tev-320B ``` How to use it: Run the model as an agent. It receives a terminal task in a container and answers with bash commands, turn by turn. The card describes this one-tool setting but shows no run commands. ```sh hf download gordonhu/Tev-320B ``` Example: You place the agent in a container that holds a broken data pipeline and ask it to fix the pipeline. It works through bash commands one turn at a time and its workspace gets closer to the expected state. The card does not show a sample session. For newcomers and experts: If you are new, this is an AI that works at a command line, running commands and reading the results until a task is done. The first small thing to try is reading the card's description of how Tev trains its agents. If you know the field, training uses a latent world, a hidden correct specification that grades both the final answer and every step. The reward adds 0.25 times a progress score to a pass or fail check. The trade-off is evidence: results come from the author's own subsets of Terminal-Bench, with 22 tasks in the 3.0 set and 18 in the 4.0 set. ```flow Build a task from a hidden correct world Corrupt the inputs with repairable defects The agent works in a container with bash Score each turn by progress, then the result ``` Good to know: ```chart Title: Terminal-Bench 4.0 CM subset, Pass@1 Claude Opus 5: 0.52 Pass@1 Claude Fable 5: 0.46 Pass@1 GPT-5.6 (sol): 0.39 Pass@1 Tev-320B: 0.37 Pass@1 Grok 4.6: 0.31 Pass@1 GLM-5.3-Flash: 0.29 Pass@1 Claude Opus 4.8: 0.27 Pass@1 Claude Sonnet 5: 0.19 Pass@1 ``` - Gain over its base: Pass@1 is 0.27 against 0.20 on the 3.0 subset, and 0.37 against 0.29 on the 4.0 subset. - Domains: Tev-Gym covers seven domains, from software engineering to quantum computing. - Weights: the files carry the base model's vision encoder untouched. Training and tests used text only, and no MTP weights ship with it. - License: cc-by-nc-4.0, so it is non-commercial. - Cost to run: no API key or paid service is named, but the model needs a huge amount of GPU memory. - Data it reaches: the agent runs bash in a container, so what it can reach depends on how you set that container up. - Not for: commercial use, which the license bars. ## On Hugging Face, 13 November 2026 - Task: text generation - Library: transformers - Parameters: 321B - Weights: about 643 GB in BF16; about 161 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 495 - Likes: 17 - License: cc-by-nc-4.0 - Languages: en - Based on: zai-org/GLM-5.3-Flash - Quantized versions: 2 - Tags: transformers, safetensors, glm5_next, image-text-to-text, agent, long-horizon, terminal, reinforcement-learning, text-generation, conversational ## Links - Model: https://huggingface.co/gordonhu/Tev-320B - Files: https://huggingface.co/gordonhu/Tev-320B/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download gordonhu/Tev-320B ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [gordonhu/Tev-320B on Hugging Face](https://huggingface.co/gordonhu/Tev-320B) ## 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 | | --- | --- | --- | --- | --- | --- | | Tev-320B (this page) | 495 | 17 | 321B | cc-by-nc-4.0 | 2026-10-14 | | [Axion-1.0-35B](https://mindket.com/p/20d39cd3-d70e-4356-9e1c-4185e55783b1) | 1,535 | 76 | 35.1B | apache-2.0 | 2026-11-04 | | [MiroThinker-v1.0-8B](https://mindket.com/p/db8679d4-5ac0-4ddd-866f-3066e5fefcb6) | 509 | 69 | 8.2B | mit | 2026-01-16 | | [Apodex-1.1-mini-GGUF](https://mindket.com/p/a81892fc-8560-455b-890b-8f7796f79d9b) | 479 | 22 | 35.5B | apache-2.0 | 2026-09-10 | | [VLX-Seek-1.5-10B](https://mindket.com/p/4b1edf89-b48a-4dfc-b86e-a0ee020dc119) | 137,772 | 39 | 10B | apache-2.0 | 2026-07-23 | | [Sage-A1.5](https://mindket.com/p/8f410da0-850f-4ea5-bda9-65555f4144cd) | 22,224 | 404 | 36B | apache-2.0 | 2026-10-22 | 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: 2026-10-14 - First published: 2026-09-27 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open gordonhu/Tev-320B on Hugging Face](https://huggingface.co/gordonhu/Tev-320B) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/63d40f1b-6af8-4909-9c96-9f1862166e30) - [Its page on Mindket](https://mindket.com/p/63d40f1b-6af8-4909-9c96-9f1862166e30)