---
title: gemma-2-9b-it-gptq-4bit
canonical_url: "https://www.modelscope.cn/models/LLM-Research/gemma-2-9b-it-gptq-4bit"
md_url: "https://www.modelscope.cn/models/LLM-Research/gemma-2-9b-it-gptq-4bit.md"
repository: LLM-Research/gemma-2-9b-it-gptq-4bit
last_updated: 2024-07-26
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - gemma2
architectures:
  - Gemma2ForCausalLM
parameters: 3.0B
tensor_type:
  - I32
  - BF16
  - F16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 2695
stars: 1
tags:
  - "gemma 2"
  - gptq
  - 4bit
  - gptqmodel
---

# gemma-2-9b-it-gptq-4bit

> gemma-2-9b-it-gptq-4bit - LLM-Research 在 ModelScope 开源的模型。This model has been quantized using GPTQModel. bits: 4 groupsize: 128 descact: false staticgroups: false sym: true lmhead: false damppercent: 0.01 truesequential: true modelnameorpath:…

LLM-Research/gemma-2-9b-it-gptq-4bit 是 ModelScope 魔搭社区上的 3.0B 参数text-generation模型，采用 apache-2.0 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: LLM-Research/gemma-2-9b-it-gptq-4bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 3.0B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: gemma 2, gptq, 4bit, gptqmodel
- **Downloads**: 2695
- **Stars**: 1
- **Last updated**: 2024-07-26

Source: https://www.modelscope.cn/models/LLM-Research/gemma-2-9b-it-gptq-4bit

---

This model has been quantized using [GPTQModel](https://github.com/ModelCloud/GPTQModel).
- **bits**: 4
- **group_size**: 128
- **desc_act**: false
- **static_groups**: false
- **sym**: true
- **lm_head**: false
- **damp_percent**: 0.01
- **true_sequential**: true
- **model_name_or_path**: 
- **model_file_base_name**: model
- **quant_method**: gptq
- **checkpoint_format**: gptq
- **meta**: 
  - **quantizer**: gptqmodel:0.9.2