software catalog

Updated Sep 1, 2026

Model Catalog

← Docs index

Copy the complete docker run from the Intel® Software Catalog. Open the model you want and use the Deployment tab.

This table is informational — use it to look up the Docker image name.

ModelDescriptionLicenseHF token requiredTagsDocker Image
google/gemma-4-E4B-itMultimodal, instruction-tuned model from Google's Gemma family with the E4B (Effective 4B) architecture, supporting text and image inputs for chat.Apache-2.0Notext-generation, chat, instruction, multimodalintel/inference-xeon-google-gemma-4-e4b-it:0.1.0
ibm-granite/granite-3.2-2b-instruct2B-parameter instruction-tuned model from IBM's Granite 3.2 series, with a built-in toggle for extended chain-of-thought reasoning.Apache-2.0Notext-generation, chat, instruction, reasoningintel/inference-xeon-ibm-granite-granite-3.2-2b-instruct:0.1.0
meta-llama/Llama-3.1-8B-Instruct8B-parameter instruction-tuned chat model from Meta's Llama 3.1 family, optimized for multilingual dialogue and tool use.Llama 3.1 Community LicenseYestext-generation, chat, instructionintel/inference-xeon-meta-llama-llama-3.1-8b-instruct:0.1.0
meta-llama/Llama-3.2-3B-InstructLightweight 3B instruction-tuned model from Meta's Llama 3.2 family, suited for on-device and latency-sensitive chat use cases.Llama 3.2 Community LicenseYestext-generation, chat, instructionintel/inference-xeon-meta-llama-llama-3.2-3b-instruct:0.1.0
microsoft/Phi-4-reasoningReasoning-focused variant of Microsoft's Phi-4 model, tuned with chain-of-thought techniques for complex multi-step problem solving.MITNotext-generation, chat, instruction, reasoningintel/inference-xeon-microsoft-phi-4-reasoning:0.1.0
mistralai/Mistral-7B-Instruct-v0.27B-parameter instruction-tuned model from Mistral AI, optimized for general-purpose chat and instruction following.Apache-2.0Notext-generation, chat, instructionintel/inference-xeon-mistralai-mistral-7b-instruct-v0.2:0.1.0
openai/gpt-oss-20b20B-parameter open-weight reasoning model from OpenAI's gpt-oss series, tuned for chain-of-thought reasoning and agentic tool use.Apache-2.0Notext-generation, chat, instruction, reasoningintel/inference-xeon-openai-gpt-oss-20b:0.1.0
Qwen/Qwen3-30B-A3BMixture-of-experts language model from Alibaba's Qwen3 series (30B total / 3B active parameters), tuned for efficient reasoning and dialogue.Apache-2.0Notext-generation, chat, instruction, reasoningintel/inference-xeon-qwen-qwen3-30b-a3b:0.1.0
Qwen/Qwen3-4B4B-parameter dense language model from Alibaba's Qwen3 series with dual thinking/non-thinking modes for reasoning and efficient dialogue.Apache-2.0Notext-generation, chat, instruction, reasoningintel/inference-xeon-qwen-qwen3-4b:0.1.0
Qwen/Qwen3-8B8B-parameter dense language model from Alibaba's Qwen3 series with dual thinking/non-thinking modes for reasoning and chat.Apache-2.0Notext-generation, chat, instruction, reasoningintel/inference-xeon-qwen-qwen3-8b:0.1.0
Qwen/Qwen3-VL-30B-A3B-InstructMultimodal vision-language mixture-of-experts model from Qwen3-VL (30B total / 3B active parameters), instruction-tuned for image-and-text chat.Apache-2.0Notext-generation, chat, instruction, multimodalintel/inference-xeon-qwen-qwen3-vl-30b-a3b-instruct:0.1.0