Model reference · open weights
ContextPilot-E is an open-weight language model from tencent, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
ContextPilot-E4B ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL src="https://img.shields.io/badge/ContextPilot-GitHub-blue?logo=github" alt="GitHub Repo" / src="https://img.shields.io/badge/ContextPilot-LiveDemo-ff725e?logo=githubpages&logoColor=white" alt="ContextPilot Live Demo" / src="https://img.shields.io/badge/ContextPilot-Paper-red?logo=arxiv&logoColor=red" alt="Paper" / src="https://img.shields.io/badge/ContextPilot-Models-yellow?logo=huggingface&logoColor=yellow" alt="Hugging Face Models" / ContextPilot-E4B is the Gemma4-E4B checkpoint of ContextPilot, a proactive context-management framework for long-horizon language-model agents. It teaches agents to plan, maintain long-term memory, and offload less useful context while they continue reasoning and using tools. For more details, see our paper and code repository. Overview ContextPilot combines three main components: - an extended context-management toolset with planning, structured memory, retrieval, and soft context offloading; - context-aware partial rollout that focuses exploration on sensitive context-editing decisions; and - fine-grained credit assignment that trains intermediate snapshots using the outcomes of their downstream branches. The resulting agents are evaluated on long-context question answering and deep-search tasks; see the evaluation instructions for details. Loading Note that loading the checkpoint alone does not execute context-management tools; the tool definitions, agent runtime, and evaluation pipeline are provided in the ContextPilot repository. See the inference guide for the full setup. Intended Use This checkpoint is intended for research on proactive context management, long-horizon agents, long-context QA, and deep search. License LICENSE. Citation
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | tencent |
|---|---|
| Type | Language models |
| Parameters (lead) | 7.9B |
| Variants | 1 |
| Runs with | transformers |
| Based on | google/gemma-4-E4B-it |
| Released | 2026-08-27 |
| Likes | 2 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| ContextPilot-E4B | 7.9B | BF16 | ~18.3 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys contextpilot-e for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (contextpilot-e below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"contextpilot-e","messages":[{"role":"user","content":"Hello"}]}'
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗