# LLM index

Lambda's catalog of model cards for the LLMs that matter. Search by model name to get architecture breakdowns, hardware requirements, deployment guides, and throughput benchmarks on NVIDIA GPUs.

## Models

- [**thinkingmachines/Inkling-NVFP4**](https://lambda.ai/inference-models/thinkingmachines/inkling-nvfp4)  
- [**tencent/Hy3-FP8**](https://lambda.ai/inference-models/tencent/hy3-fp8)  
- [**zai-org/GLM-5.2**](https://lambda.ai/inference-models/zai-org/glm-5.2)  
- [**moonshotai/Kimi-K2.7-Code**](https://lambda.ai/inference-models/moonshotai/kimi-k2.7-code)  
- [**MiniMaxAI/MiniMax-M3**](https://lambda.ai/inference-models/minimaxai/minimax-m3)  
- [**nvidia/nemotron-3-ultra**](https://lambda.ai/inference-models/nvidia/nemotron-3-ultra)  
- [**LiquidAI/LFM2.5-8B-A1B**](https://lambda.ai/inference-models/liquidai/lfm2.5-8b-a1b)  
- [**HuggingFaceBio/Carbon-3B**](https://lambda.ai/inference-models/huggingfacebio/carbon-3b)  
- [**stepfun-ai/Step-3.7-Flash**](https://lambda.ai/inference-models/stepfun-ai/step-3.7-flash)  
- [**moonshotai/Kimi-K2.6**](https://lambda.ai/inference-models/moonshotai/kimi-k2.6)