Mistral AIconfiguration verified
Mistral 7B Instruct
mistralai/Mistral-7B-Instruct-v0.3- chat
- tools
Verified Models
Choose a model.
Keep the evidence visible.
Start from a reviewed repository, immutable revision, license, protocol, and runtime configuration. InferCrane never turns a convenient template into an unsupported performance, price, or provider claim.
infercrane modelsinfercrane models inspect mistral-7b-instructinfercrane workload init ./support-model --recipe mistral-7b-instructChat8Assistants and generation
Reasoning2Analysis and multi-step tasks
Coding1Completion and repair
Vision2Images and documents
Embeddings1Search and private RAG
Qwenconfiguration verified
Qwen3 8B
Qwen/Qwen3-8B- chat
- reasoning
- tools
BAAIconfiguration verified
BGE-M3
BAAI/bge-m3- embeddings
- retrieval
- RAG
Metaconfiguration verified
Llama 3.1 8B Instruct
meta-llama/Llama-3.1-8B-Instruct- chat
- tools
Qwenconfiguration verified
Qwen2.5 Coder 7B Instruct
Qwen/Qwen2.5-Coder-7B-Instruct- coding
- chat
DeepSeekconfiguration verified
DeepSeek R1 Distill Qwen 7B
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B- reasoning
- chat
Googleconfiguration verified
Gemma 3 4B IT
google/gemma-3-4b-it- vision
- chat
- documents
Qwenconfiguration verified
Qwen2.5 VL 7B Instruct
Qwen/Qwen2.5-VL-7B-Instruct- vision
- documents
- chat
IBMconfiguration verified
Granite 3.3 8B Instruct
ibm-granite/granite-3.3-8b-instruct- chat
- extraction
- summarization
Not an allowlist
Use the model your workload needs.
The catalog shortens the first deployment. The explicit path accepts another Hugging Face model or an immutable custom OCI workload and asks you to qualify it.
infercrane workload init ./my-model --model organization/repositoryinfercrane workload plan ./my-model