LLaVA

LLaVA 1.5 7B

Name: LLaVA 1.5 7B
Rating: 67 (142 reviews)
Author: LLaVA

旧版

HuggingFace

Ollama

370.2K下载量552点赞Oct 2023发布日期4K tokens上下文Apache 2.0许可证44 基础质量

LLaVA 1.5 7B (7B parameters) requires approximately 13.9 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 16 GB of VRAM.

快速开始

— 复制粘贴即可本地运行

Copy-paste commands to run LLaVA 1.5 7B on your machine.

Run

ollama run llava

Quick specs

Parameters7B

Architecturedense

Context4K tokens

Modalitytext+vision

Min RAM2.7 GB

Rec. RAM4.3 GB (Q4_K_M)

LicenseApache 2.0

FamilyLLaVA

✓ Vision✓ Chat

About this model

Model type: LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.

•558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP
•158K GPT-generated multimodal instruction-following data
•450K academic-task-oriented VQA data mixture
•40K ShareGPT data

LLaVA 1.5 7B 的最佳选择

运行此模型

LLaVA 1.5 7B on RX 7900 XT 20GB LLaVA 1.5 7B on RTX A4500 20GB LLaVA 1.5 7B on RTX 3090 24GB

量化选项

各量化级别的 VRAM 估算

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	—
Q3_K_S	3	3.4 GB	Low	—
NVFP4	4	3.9 GB	Medium	—
Q4_K_M	4	4.3 GB	Medium	—
Q5_K_M	5	5.0 GB	High	—
Q6_K	6	5.7 GB	High	—
Q8_0	8	7.5 GB	Very High	—
F16	16	14.3 GB	Maximum	—

硬件兼容性

全部硬件的适配估算

打开计算器

Computing compatibility...

内存详细分析

Reference: RTX 2060 6GB

Weights4.3 GB

KV Cache7.8 GB

Runtime1.2 GB

Headroom0.6 GB

常见问题

FAQ — LLaVA 1.5 7B

另请参阅

量化指南评分方法打开计算器