DeepSeek-V3

Mistral NeMo

Mistral NeMo is the NVIDIA-optimized deployment of Mistral models, packaged as NeMo/NIM microservices for fast, scalable inference. It brings long-context prompting, tool/function calling, and reliable JSON output with TensorRT-LLM acceleration, quantization, and easy autoscaling on NVIDIA GPUs.

Text New

Qwen3-235B-A22B

Qwen3-235B-A22B is Alibaba’s flagship open-source MoE LLM (Apache-2.0): 235B total parameters with 22B activated (128 experts, 8 active). It uniquely toggles thinking vs. non-thinking modes, supports 100+ languages, and excels at agentic tool use. Context is 32K native (≈131K with YaRN); the Instruct-2507 variant offers 256K native and up to ~1M tokens.

Text New

OPT

No description available.

Text