---
title: LocoOperator-4B-NVFP4
canonical_url: "https://www.modelscope.cn/models/DJLougen/LocoOperator-4B-NVFP4"
md_url: "https://www.modelscope.cn/models/DJLougen/LocoOperator-4B-NVFP4.md"
repository: DJLougen/LocoOperator-4B-NVFP4
last_updated: 2026-04-07
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3
architectures:
  - Qwen3ForCausalLM
base_model:
  - LocoreMind/LocoOperator-4B
base_model_relation: quantized
parameters: 2.4B
tensor_type:
  - U8
  - F32
  - F8_E4M3
  - BF16
library_name:
  - transformer
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 16
stars: 0
tags:
  - nvfp4
  - quantized
  - qwen3
  - agent
  - tool-calling
  - code
  - nvidia
  - modelopt
  - spark
---

# LocoOperator-4B-NVFP4

> LocoOperator-4B-NVFP4 - DJLougen 在 ModelScope 开源的模型。LocoOperator-4B — NVFP4 Quantized

DJLougen/LocoOperator-4B-NVFP4 是 ModelScope 魔搭社区上的 2.4B 参数text-generation模型，采用 mit 许可，基于 LocoreMind/LocoOperator-4B 构建，可用 deploy_task text/emb、lmdeploy_turbomind 0.9.1、sglang 0.5.2 部署。

- **Repository**: DJLougen/LocoOperator-4B-NVFP4
- **License**: mit
- **Tasks**: text-generation
- **Parameters**: 2.4B
- **Base model**: LocoreMind/LocoOperator-4B
- **Inference backends**: deploy_task text/emb, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: nvfp4, quantized, qwen3, agent, tool-calling, code, nvidia, modelopt, spark
- **Downloads**: 16
- **Stars**: 0
- **Last updated**: 2026-04-07

Source: https://www.modelscope.cn/models/DJLougen/LocoOperator-4B-NVFP4

---

# LocoOperator-4B — NVFP4 Quantized

NVFP4-quantized version of [LocoreMind/LocoOperator-4B](https://huggingface.co/LocoreMind/LocoOperator-4B), an agent/tool-calling model based on Qwen3-4B-Instruct.

## Quantization Details

| Property | Value |
|----------|-------|
| **Base model** | LocoreMind/LocoOperator-4B (Qwen3-4B finetune) |
| **Quantization** | NVFP4 (weights) + FP8 (KV cache) |
| **Group size** | 16 |
| **Tool** | NVIDIA TensorRT Model Optimizer (modelopt 0.35.0) |
| **Calibration** | cnn_dailymail (default) |
| **Original size** | ~8 GB (BF16) |
| **Quantized size** | 2.7 GB |
| **Excluded** | `lm_head` (kept in higher precision) |

## Intended Use

Optimized for deployment on NVIDIA Blackwell GPUs (GB10/GB100), particularly the DGX Spark. The NVFP4 format leverages Blackwell's native FP4 tensor cores for maximum throughput.

Best suited for:
- Agent/tool-calling workflows
- Code generation
- Instruction following

## Usage

### With transformers + modelopt

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "DJLougen/LocoOperator-4B-NVFP4",
    device_map="auto",
    torch_dtype="auto",
)
tokenizer = AutoTokenizer.from_pretrained("DJLougen/LocoOperator-4B-NVFP4")
```

### With TensorRT-LLM

Convert to TensorRT-LLM engine for optimal inference performance on Spark/Blackwell hardware.

## Quality Check

Example outputs (cnn_dailymail calibration text):

**Before quantization:**
> "I'm excited to be doing the final two films," he said. "I can't wait to see what happens."

**After NVFP4 quantization:**
> "I don't think I'll be particularly extravagant," Radcliffe said. "I don't think I'll be one of those people who, as soon as they turn 18, suddenly buy themselves a massive sports car collection or something similar."

Both outputs are coherent and contextually appropriate.

## Hardware

- **Quantized on:** NVIDIA DGX Spark (GB10, 128 GB unified memory)
- **Docker image:** `nvcr.io/nvidia/tensorrt-llm/release:spark-single-gpu-dev`
- **Target deployment:** Any NVIDIA Blackwell GPU with FP4 tensor core support