Downloads · 30 days
0
Qwen3-4B-AWQ-TensorRT-EdgeLLM-engine
harvestsu/Qwen3-4B-AWQ-TensorRT-EdgeLLM-engine
Qwen3-4B-AWQ-TensorRT-EdgeLLM-engine is a machine learning model from harvestsu. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for tensorrt. The card lists the license as other.
This repository contains the TensorRT-EdgeLLM engine artifacts for Qwen/Qwen3-4B-AWQ on Jetson Orin.
Access
Public
Updated May 17, 2026
Repo size
6.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.engine2.7 GB · 77%
At a glance
- Library
- tensorrt
- License
- other
- Model type
- llm
- Access
- Public
- Created
- May 17, 2026
- Updated
- May 17, 2026
- SHA
- e6772bb2
Model card
From the Hugging Face model README
Qwen3-4B-AWQ TensorRT-EdgeLLM Engine
This repository contains the TensorRT-EdgeLLM engine artifacts for
Qwen/Qwen3-4B-AWQ on Jetson Orin.
Runtime compatibility:
- TensorRT:
10.3.0.30-1+cuda12.5 - CUDA runtime: JetPack host CUDA 12.x
- Target GPU: Orin, compute capability 8.7
- TensorRT-Edge-LLM commit:
7d6579c8293c5cc62986238aa200ea9c7b57d50a - Engine config: max batch size 1, max input length 3072, KV cache capacity 4096
The engine must be used with a matching TensorRT-EdgeLLM runtime/plugin build.
It is consumed by the edge-llm-chat-service container via
EDGELLM_ENGINE_REPO.
- Library
- tensorrt
- Type
- llm
- License
- other
- Created
- May 17, 2026
- Updated
- May 17, 2026