UO
University of Wisconsin Madison
Multimodal model · United States ·Apr 2023

LLaVA

Multimodal Open (Restricted)
13B
Parameters

About LLaVA

LLaVA is an AI model developed by University of Wisconsin Madison, in the multimodal category, released in 2023, made available as an open-weights model with 13B params.

On this page you'll find LLaVA's full specifications. Review provider pricing and benchmark scores below, or compare LLaVA head-to-head with other multimodal models.

→ More models by University of Wisconsin Madison → All multimodal models → AI benchmarks leaderboard

Links

Announcement ↗

Run LLaVA locally — what to buy

Share this build ↗

Sized to what LLaVA actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good
Intel Arc B580 12GB
Consumer GPU · ~$249
~45.1 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
Intel Arc A770 16GB
Consumer GPU · ~$329
~55.4 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
NVIDIA GeForce RTX 4090
Consumer GPU · ~$1,599
~120 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
22.2–120+ tok/s
28 options →
Apple
33.8–90.1 tok/s
17 options →
Datacenter GPU
91.4–120+ tok/s
13 options →

Community

Would you run LLaVA again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like LLaVA

AI
NeuroChess
· 72.3K
 UO
ProteinSetTransformer
University of Wisconsin Madison
 UO
METL-Global
University of Wisconsin Madison · 50M
 UO
LLaVA-NeXT-34B (LLaVA-1.6)
University of Wisconsin Madison · 34.8B
 UO
LLaVA 1.5
University of Wisconsin Madison · 13B
 UO
HOGWILD!
University of Wisconsin Madison

Frequently asked questions

What is LLaVA? ▶

LLaVA is an AI model developed by University of Wisconsin Madison, in the multimodal category, released in 2023. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created LLaVA? ▶

LLaVA was developed by University of Wisconsin Madison and released in 2023.

Is LLaVA open source or proprietary? ▶

LLaVA ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does LLaVA cost? ▶

Pricing for LLaVA depends on the provider. See the providers table on this page for the latest API rates.

How does LLaVA perform on benchmarks? ▶

Benchmark scores for LLaVA are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

No videos yet. Know a good one? Add it below.

Know a great video about LLaVA?