Models
Open models we plan to serve on CPUs. Each one is tagged not live yet. Context lengths are omitted until we confirm them from the model cards.
| Name | API id | Hugging Face id | Type | Size | License | Status |
|---|---|---|---|---|---|---|
| LFM3-1.7B | lfm3-1.7b | LiquidAI/LFM3-1.7B | Chat | 1.73B | LFM Open License | Not live yet |
| LFM2.5-8B-A1B | lfm2.5-8b-a1b | LiquidAI/LFM2.5-8B-A1B | Chat | 8.47B total, 1B-class active | LFM Open License | Not live yet |
| Qwen3.5-4B | qwen3.5-4b | Qwen/Qwen3.5-4B | Chat | 4.66B | Apache 2.0 | Not live yet |
| Qwen3-8B | qwen3-8b | Qwen/Qwen3-8B | Chat | 8.19B | Apache 2.0 | Not live yet |
| Gemma 4 E4B it | gemma-4-e4b-it | google/gemma-4-E4B-it | Chat | 4.5B effective, 8.0B with embeddings | Apache 2.0 | Not live yet |
| Llama 3.1 8B Instruct | llama-3.1-8b-instruct | meta-llama/Llama-3.1-8B-Instruct | Chat | 8.03B | Llama 3.1 Community License | Not live yet |
| gpt-oss-20b | gpt-oss-20b | openai/gpt-oss-20b | Chat | 21B total, 3.6B active | Apache 2.0 | Not live yet |
| Qwen3-Coder-30B-A3B Instruct | qwen3-coder-30b-a3b-instruct | Qwen/Qwen3-Coder-30B-A3B-Instruct | Coding | 30.5B total, 3B-class active | Apache 2.0 | Not live yet |
| BGE-M3 | bge-m3 | BAAI/bge-m3 | Embeddings | 567M | MIT | Not live yet |
| nomic-embed-text-v1.5 | nomic-embed-text-v1.5 | nomic-ai/nomic-embed-text-v1.5 | Embeddings | 137M | Apache 2.0 | Not live yet |
| BGE reranker v2 M3 | bge-reranker-v2-m3 | BAAI/bge-reranker-v2-m3 | Reranker | 0.57B | Apache 2.0 | Not live yet |
| Whisper large-v3-turbo | whisper-large-v3-turbo | openai/whisper-large-v3-turbo | Speech | 0.81B | MIT | Not live yet |