GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
JIT-Agent
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
JIT-Agent
Model Tree
Qwen/Qwen3.6-27B
Input Modalities
Output Modalities
Supported Functionality
This repository contains the initial research release of JIT-Agent-27B. The checkpoint builds on the Stage-I harness-customization model and is further trained through distillation from the final research checkpoint.
| Property | Value |
|---|---|
| Base model | Qwen/Qwen3.6-27B |
| Parameters | 27.36B |
| Weight precision | BF16 |
| Architecture context length | 262,144 tokens |
| Recommended serving context | 163,840 tokens |
| Primary input | Task, tools, protocol, and reference-harness descriptions |
| Primary output | Four Python modules and one YAML prompt configuration |
JIT-Agent generates harnesses under a fixed four-module protocol:
memory.py: constructs and updates the agent's working context;planning.py: forms directives and manages plan state;action.py: implements the task-execution loop;tool_policy.py: controls tool and skill exposure;prompt.yaml: defines the prompts consumed by the generated modules.The model emits these files using the following tagged format:
text
<<<PYTHON_MEMORY>>>...<<<END_PYTHON_MEMORY>>><<<PYTHON_PLANNING>>>...<<<END_PYTHON_PLANNING>>><<<PYTHON_ACTION>>>...<<<END_PYTHON_ACTION>>><<<PYTHON_TOOL_POLICY>>>...<<<END_PYTHON_TOOL_POLICY>>><<<YAML>>>...<<<END_YAML>>>
The checkpoint is designed to be used with the JIT-Agent runtime, which constructs the full generation prompt, validates the structured output, installs the resulting harness, and executes it against an off-the-shelf agentic model.
bash
git clone https://github.com/bingreeky/JIT.gitcd JITconda env create -f environment.ymlconda activate jit
The repository provides a vLLM launcher with the recommended serving settings:
bash
MODEL=JIT-Agent/jit-27b \TP=4 \bash scripts/serve_meta_model.sh
This exposes an OpenAI-compatible endpoint at http://localhost:8000/v1.
bash
python -m scripts.run_jit \--bench xbench \--meta-model jit \--meta-base http://localhost:8000/v1 \--harness-refs desc \--max-samples 5
The released checkpoint should be used with description references:
text
--harness-refs desc
In this mode, the model receives natural-language design descriptions of the reference harnesses rather than their source code. This is also the default mode of the released runtime.
For best-of-N inference, the runtime generates three candidate harnesses at temperature 1.0 and selects one before task execution.
JIT-Agent-27B is intended for research on:
It is a harness generator rather than a general-purpose chat model. Direct chat-style prompting without the accompanying protocol and runtime context is unlikely to produce valid executable harnesses. Also see here.
The checkpoint is released under the Apache License 2.0. It is derived from
Qwen/Qwen3.6-27B, which is also
released under Apache 2.0.