LLaVA

LLaVA 1.5 7B

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

レガシー

HuggingFace

Ollama

370.2Kダウンロード552いいねOct 2023公開日4K トークンコンテキストApache 2.0ライセンス44 基本品質

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.

はじめに

— コピー&ペーストでローカル実行

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のおすすめ

このモデルを実行

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

量子化オプション

量子化レベル別VRAM推定値

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	—

ハードウェア互換性

全ハードウェアの適合度推定

カリキュレーターを開く

Computing compatibility...

メモリ内訳

Reference: RTX 2060 6GB

Weights4.3 GB

KV Cache7.8 GB

Runtime1.2 GB

Headroom0.6 GB

よくある質問

LLaVA 1.5 7B

LLaVA 1.5 7Bのおすすめ

量子化レベル別VRAM推定値

全ハードウェアの適合度推定

Reference: RTX 2060 6GB

FAQ — LLaVA 1.5 7B