# Model Serving - Decommissioned Models

The models listed here have been permanently decommissioned and are no longer available on the Phoeniqs Model Service. Requests to these models will return an error. Please use a supported model from the Active Models list.


# Decommissioned Models

Model Name Decommissioned Date Type
inference-multilingual-e5-large, intfloat/multilingual-e5-large 02.12.2024 Embedding
inference-teuken-7b, openGPT-X/Teuken-7B-instruct 16.05.2025 Chat
inference-phi-4, RedHatAI/phi-4-quantized.w4a16 09.01.2026 Chat
inference-apertus-8b, swiss-ai/Apertus-8B-Instruct-2509 28.05.2026 Chat
inference-deepseekr1-70b, RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16 28.05.2026 Chat
inference-deepseekr1-670b, RedHatAI/DeepSeek-R1-0528-quantized.w4a16 28.05.2026 Chat
inference-kimi-k2, RedHatAI/Kimi-K2-Instruct-quantized.w4a16 28.05.2026 Chat only
inference-llama33-70b, RedHatAI/Llama-3.3-70B-Instruct-quantized.w4a16 28.05.2026 Chat only
inference-qwq25-vl-72b, RedHatAI/Qwen2.5-VL-72B-Instruct-quantized.w4a16 28.05.2026 Multimodal
inference-glm-51-754b, zai-org/GLM-5.1 07.07.2026 Reasoning & Coding
inference-apertus-70b, RedHatAI/Apertus-70B-Instruct-2509-quantized.w4a16 21.08.2026 Chat

NOTE For models recently scheduled for removal but still reachable on demand, see the Scheduled for Retirement list.