LLMs · LLaVA

LLaVA 1.6 Mistral 7B

Name: LLaVA 1.6 Mistral 7B
Author: LLaVA

Parameters: 7.6B
Architecture: Dense
Max context: 32K tokens
License: apache-2.0
Released: 2024-02

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:7b-v1.6-mistral-q4_K_M

Original weights · Hugging Face

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

huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf (opens in a new tab)

No sign-in needed.

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

Apps that run LLaVA 1.6 Mistral 7B

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:7b-v1.6-mistral-q4_K_M`
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve llava-hf/llava-v1.6-mistral-7b-hf`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path llava-hf/llava-v1.6-mistral-7b-hf`
Docker Model Runner	CLI + API	Original weights	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/llava-hf/llava-v1.6-mistral-7b-hf`
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 8K context	Total at 32K context	Download
`Q2_K`	Low	3.0 GB	4.7 GB	7.9 GB
`Q3_K_M`	Low	3.7 GB	5.4 GB	8.6 GB
`Q4_K_M`	Good	4.6 GB	6.3 GB	9.5 GB
`Q5_K_M`	High	5.4 GB	7.0 GB	10.3 GB
`Q6_K`	High	6.2 GB	7.9 GB	11.1 GB
`Q8_0`	Very high	8.0 GB	9.7 GB	12.9 GB
`F16`	Full	15.1 GB	16.8 GB	20.0 GB	Original weights (opens in a new tab)

Best hardware for LLaVA 1.6 Mistral 7B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q2_K.

Quality	Hardware	Quant	Memory	Speed	Runs
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 9070 XT	`Q8_0`	10.5 GB / 16.0 GB	45.5 tok/s	Runs great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4070 Ti SUPER	`Q8_0`	10.5 GB / 16.0 GB	55.5 tok/s	Runs great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4080 SUPER	`Q8_0`	10.5 GB / 16.0 GB	60.8 tok/s	Runs great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5070 Ti	`Q8_0`	10.5 GB / 16.0 GB	74.0 tok/s	Runs great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5080	`Q8_0`	10.5 GB / 16.0 GB	79.2 tok/s	Runs great
27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 3060 12GB	`Q6_K`	8.5 GB / 12.0 GB	40.5 tok/s	Runs great
27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4070 SUPER	`Q6_K`	8.5 GB / 12.0 GB	56.7 tok/s	Runs great
27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	Intel Arc B580	`Q6_K`	8.5 GB / 12.0 GB	39.2 tok/s	Runs great
26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4060	`Q4_K_M`	6.7 GB / 8.0 GB	44.1 tok/s	Runs great
28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5090	`F16`	18.4 GB / 32.0 GB	68.2 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.