Text

Vicuna

One of the first open chat models (2023): LLaMA fine-tuned on user conversations with ChatGPT. A historical milestone; today it is weaker than any modern model of the same size.

The last open version came out in Aug 2023. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
LMSYS (Berkeley and partners), USA
First release
Apr 2023
Latest release
Aug 2023
Sizes
7B – 33B
License
Commercial use with conditionsv1.5: Llama 2 Community License; early LLaMA 1 versions (v0 released only as weight deltas): non-commercial
Russian
Not supported
Ready-made builds
GGUF, GPTQ
Running
Available in OllamaNeeds a GPU
Industries
Customer support, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Experiments and team training
  • Simple chat assistant for tests
  • Comparison with newer models

Where it is used

R&DEducation

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Vicuna v1.5 16K
  2. Vicuna v1.5 (Llama 2)
  3. Vicuna v1.3 (7B / 13B / 33B)
  4. Vicuna v1.1
  5. Vicuna v0 (разница весов)

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Vicuna be used in a commercial project?

With conditions. License: v1.5: Llama 2 Community License; early LLaMA 1 versions (v0 released only as weight deltas): non-commercial. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Vicuna need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Vicuna support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Vicuna and what does it cost?

The Vicuna weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

TextLlamaMeta · USACommercial use with conditions

The models that started mass open source in AI. A huge ecosystem of fine-tuned versions and tools.

DetailsTextOpenChatOpenChat (Tsinghua University) · ChinaCommercial use with conditions

Fine-tunes of Mistral 7B and Llama 3 8B using the C-RLFT method that caught up with ChatGPT-3.5 in 2023–2024 at just 7–8B. A lightweight general-purpose assistant for a modest server.

DetailsTextZephyrHugging Face (H4) · USACommercial use allowed

Hugging Face educational chat models based on Mistral, Gemma and Mixtral with an open fine-tuning recipe. Zephyr 7B Beta showed a small model can be trained to large-model level without human labeling.

Details

Source: huggingface.co/lmsys/vicuna-13b-v1.5-16k. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.