Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.oumi.ai/llms.txt

Use this file to discover all available pages before exploring further.

The following is a list of models available on the Oumi platform, organized by use case, with more supported models added continuously. For the most up-to-date list, ask the Oumi Agent with this prompt:
List all currently supported Oumi models, organized by use case, including any newly added models.

TRAINING (FINE-TUNING BASE MODELS)

Oumi supports a broad set of models that can be fine-tuned on your own data, with each model offering different training approaches and requirements depending on its architecture and capabilities.
ModelTraining methods
Qwen/Qwen3.5-9BSFT (FFT)
Qwen/Qwen3.5-9B-BaseSFT (FFT)
Qwen/Qwen3.5-4BSFT (FFT)
Qwen/Qwen3.5-4B-BaseSFT (FFT)
Qwen/Qwen3.5-2BSFT (FFT)
Qwen/Qwen3.5-0.8BSFT (FFT)
Qwen/Qwen3-32BSFT (LoRA)
Qwen/Qwen3-8BSFT (LoRA, FFT), OPD
Qwen/Qwen3-4B-Instruct-2507SFT (LoRA, FFT), OPD
Qwen/Qwen3-0.6BSFT (LoRA, FFT), OPD
Qwen/Qwen2.5-7B-InstructSFT (LoRA, FFT), OPD
Qwen/Qwen2.5-7BSFT (LoRA, FFT), OPD
Qwen/Qwen2.5-3B-InstructSFT (LoRA, FFT), OPD
Qwen/Qwen2.5-1.5B-InstructSFT (LoRA, FFT), OPD
meta-llama/Llama-4-Scout-17B-16E-InstructSFT (LoRA)
meta-llama/Llama-3.1-8B-InstructSFT (LoRA, FFT), OPD
meta-llama/Llama-3.2-3B-InstructSFT (LoRA, FFT), OPD
meta-llama/Llama-3.2-1B-InstructSFT (LoRA, FFT), OPD
google/gemma-3-4b-itSFT (LoRA, FFT)
microsoft/Phi-3.5-mini-instructSFT (LoRA, FFT)
microsoft/Phi-3.5-MoE-instructSFT (LoRA)
openai/gpt-oss-20bSFT (FFT)
HuggingFaceTB/SmolLM2-1.7B-InstructSFT (LoRA, FFT)
HuggingFaceTB/SmolLM2-360M-InstructSFT (LoRA, FFT), OPD
HuggingFaceTB/SmolLM2-135M-InstructSFT (LoRA, FFT), OPD
HuggingFaceTB/SmolLM-1.7B-InstructSFT (LoRA, FFT)
HuggingFaceTB/SmolLM-360M-InstructSFT (LoRA, FFT)
HuggingFaceTB/SmolLM-135M-InstructSFT (LoRA, FFT)

INFERENCE (EVALUATION, SYNTHESIS, AND COMPLETIONS)

The following models are available for evaluation judges, data synthesis, and generating completions.
You can unlock access to frontier models for inference by adding API keys for major providers.
ModelProvider
Qwen/Qwen3.5-397B-A17Boumi
Qwen/Qwen3.5-9Boumi
Qwen/Qwen3-235B-A22B-Instruct-2507oumi
deepseek-ai/DeepSeek-V3.1oumi
moonshotai/Kimi-K2.5oumi
openai/gpt-oss-120boumi
zai-org/GLM-5.1oumi
zai-org/GLM-5oumi
zai-org/GLM-4.6oumi
meta-llama/Llama-3.3-70B-Instructoumi
Qwen/Qwen2.5-7B-Instructoumi
mistralai/Mixtral-8x7B-Instruct-v0.1oumi
All models available as a training base can also be used for evaluation.
Can’t find the model you’re looking for? Reach out to us at support@oumi.ai with your request.