TextCodeMath and reasoning

WizardLM, WizardCoder, WizardMath

Fine-tunes of Llama, Mistral and StarCoder using Evol-Instruct, which automatically makes instructions more complex. WizardLM-2 was released in April 2024 and removed almost immediately, so only the 2023 versions are relevant.

The last open version came out in Jan 2024. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
WizardLM (Microsoft and Peking University), USA / China
First release
May 2023
Latest release
Jan 2024
Sizes
7B – 70B
License
Commercial use with conditionsDepends on the base: Llama 2 versions: Llama 2 Community License; WizardCoder 33B: DeepSeek license; early LLaMA 1 versions: non-commercial
Russian
Not supported
Ready-made builds
GGUF
Running
Available in OllamaNeeds a GPU
Industries
Software development, Science and research, Education
Deploy on your server Hugging Face GitHub

What it does

  • Complex multi-step instructions
  • Help for developers
  • Solving math problems
  • Experiments with fine-tuning methods

Where it is used

IT departmentEducationR&D

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. WizardCoder 33B V1.1
  2. WizardMath 7B V1.1 (Mistral)
  3. WizardLM 70B, WizardMath 70B, WizardCoder Python 34B
  4. WizardLM 13B V1.2
  5. WizardCoder 15B
  6. WizardLM 13B V1.0

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 WizardLM, WizardCoder, WizardMath be used in a commercial project?

With conditions. License: Depends on the base: Llama 2 versions: Llama 2 Community License; WizardCoder 33B: DeepSeek license; early LLaMA 1 versions: non-commercial. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does WizardLM, WizardCoder, WizardMath 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 WizardLM, WizardCoder, WizardMath support Russian?

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

Where can I download WizardLM, WizardCoder, WizardMath and what does it cost?

The WizardLM, WizardCoder, WizardMath 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

TextVicunaLMSYS (Berkeley and partners) · USACommercial use with conditions

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.

DetailsCodeCode LlamaMeta · USACommercial use with conditions

A version of Llama 2 further trained on code, with variants for Python and for chat. Outdated, but many ready-made fine-tuned versions and tools exist.

DetailsTextHermesNous Research · USACommercial use with conditions

Nous Research fine-tunes on top of Llama, Mistral, Qwen and Seed-OSS. Valued for precise instruction following, function calling and strict JSON output; they refuse less often than the originals; Hermes 4 has a reasoning mode.

Details

Source: huggingface.co/WizardLMTeam/WizardCoder-33B-V1.1. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.