LLMs · LLaVA

LLaVA 1.5 13B

Name: LLaVA 1.5 13B
Author: LLaVA

Parameters: 13B
Architecture: Dense
Max context: 4K tokens
License: llama2
Released: 2023-10

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run llava:13b-v1.5-q4_K_M

Original weights · Hugging Face

Full-precision files from LLaVA, for fine-tuning, vLLM, Transformers.

huggingface.co/liuhaotian/llava-v1.5-13b (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

Apps that run LLaVA 1.5 13B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

Ollama

One command with Ollama’s own build of this model.

Also good:

Windows PC, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good:

Windows PC, AMD Radeon

Ollama

One command with Ollama’s own build of this model.

Also good:

Linux, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App	Type	Opens it as	Systems	Engine	Start
Ollama	CLI + API	Ollama library	macOSWindowsLinux	llama.cpp, MLX	`ollama run llava:13b-v1.5-q4_K_M`
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve liuhaotian/llava-v1.5-13b`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path liuhaotian/llava-v1.5-13b`
Docker Model Runner	CLI + API	Original weights	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/liuhaotian/llava-v1.5-13b`
Text Generation WebUI	Desktop app	Original weights	macOSWindowsLinux	llama.cpp, Transformers, ExLlamaV3	Get Text Generation WebUI

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

Quantization	Quality	Weights	Total at 4K context	Download
`Q2_K`	Low	5.3 GB	9.3 GB
`Q3_K_M`	Low	6.5 GB	10.5 GB
`Q4_K_M`	Good	8.1 GB	12.1 GB
`Q5_K_M`	High	9.5 GB	13.4 GB
`Q6_K`	High	10.9 GB	14.9 GB
`Q8_0`	Very high	14.2 GB	18.1 GB
`F16`	Full	26.7 GB	30.7 GB	Original weights (opens in a new tab)

Best hardware for LLaVA 1.5 13B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc B570 (launch price $219) at Q2_K.

Quality	Hardware	Quant	Memory	Speed	Runs
22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 3090	`Q8_0`	19.3 GB / 24.0 GB	43.8 tok/s	Runs great
22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4090	`Q8_0`	19.3 GB / 24.0 GB	47.2 tok/s	Runs great
21Basic quality (D) · 21 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 7900 XTX	`Q6_K`	16.1 GB / 24.0 GB	52.7 tok/s	Runs great
20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 9070 XT	`Q4_K_M`	12.9 GB / 16.0 GB	50.7 tok/s	Runs great
20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4070 Ti SUPER	`Q4_K_M`	12.9 GB / 16.0 GB	61.8 tok/s	Runs great
20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4080 SUPER	`Q4_K_M`	12.9 GB / 16.0 GB	67.7 tok/s	Runs great
20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5060 Ti 16GB	`Q4_K_M`	12.9 GB / 16.0 GB	41.2 tok/s	Runs great
20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5070 Ti	`Q4_K_M`	12.9 GB / 16.0 GB	82.4 tok/s	Runs great
20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5080	`Q4_K_M`	12.9 GB / 16.0 GB	88.3 tok/s	Runs great
22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5090	`Q8_0`	19.7 GB / 32.0 GB	83.9 tok/s	Runs great

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.