---
title: llava-v1.6-34b-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/llava-v1.6-34b-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/llava-v1.6-34b-8bit.md"
repository: mlx-community/llava-v1.6-34b-8bit
last_updated: 2024-12-19
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - llava_next
architectures:
  - LlavaNextForConditionalGeneration
parameters: 9.8B
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy 0.9.1"
  - "vllm 0.9.2"
downloads: 1006
stars: 0
tags:
  - vision
  - image-text-to-text
  - mlx
---

# llava-v1.6-34b-8bit

> llava-v1.6-34b-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/llava-v1.6-34b-8bit This model was converted to MLX format from llava-hf/llava-v1.6-34b-hf using mlx-vlm version 0.1.0. Refer to the original model card for more details on the model. Use…

mlx-community/llava-v1.6-34b-8bit 是 ModelScope 魔搭社区上的 9.8B 参数image-text-to-text模型，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、vllm 0.9.2 部署。

- **Repository**: mlx-community/llava-v1.6-34b-8bit
- **Tasks**: image-text-to-text
- **Parameters**: 9.8B
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, vllm 0.9.2
- **Tags**: vision, image-text-to-text, mlx
- **Downloads**: 1006
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/llava-v1.6-34b-8bit

---

# mlx-community/llava-v1.6-34b-8bit
This model was converted to MLX format from [`llava-hf/llava-v1.6-34b-hf`]() using mlx-vlm version **0.1.0**.
Refer to the [original model card](https://huggingface.co/llava-hf/llava-v1.6-34b-hf) for more details on the model.
## Use with mlx

```bash
pip install -U mlx-vlm
```

```bash
python -m mlx_vlm.generate --model mlx-community/llava-v1.6-34b-8bit --max-tokens 100 --temp 0.0
```