Models & Labs
NVIDIA Launches Nemotron 3 Ultra Model
Ollama Bloghigh confidence
Why it matters
- →Nemotron 3 Ultra offers unprecedented context length, enhancing its utility in complex workflows.
- →The model's efficiency in memory and speed makes it a cost-effective choice for developers.
- →Its high accuracy and throughput set a new standard for open AI models.
NVIDIA has released the Nemotron 3 Ultra, a 550 billion parameter AI model available on Ollama's cloud platform. Designed for long-running agentic workflows, it features a 1 million token context to handle extensive codebases and research trails. The model uses NVFP4, a 4-bit floating point format, to optimize memory and speed. Benchmarks show it leads in accuracy and cost efficiency, offering up to 30% savings over other models. This positions Nemotron 3 Ultra as a top choice for developers needing robust AI capabilities.
Read originalMore in Models & Labs
Models & Labsmodels
v0.22.1 fixes CUTLASS fmin compatibility
The v0.22.1 release of vLLM addresses a critical compatibility issue with CUTLASS fmin during the initialization of DeepSeek-V4. This update ensures that users relying on this configuration experience smoother integration and improved functionality. By resolving this specific technical challenge, the release contributes to the ongoing refinement and stability of the vLLM framework. Users can now expect enhanced performance and fewer compatibility problems, reinforcing the platform's reliability. This update is a testament to the continuous efforts to maintain and improve the technical robustness of vLLM.
vLLM Releases
Models & Labsmodels
llama.cpp b9509 release optimizes token processing
The b9509 release of llama.cpp brings a key optimization by preventing unnecessary checkpoint restores when new tokens are detected. This update ensures that the system only applies a conservative -1 subtraction when no new tokens are present, thereby minimizing redundant KV state restoration. Developers working with token-based tasks will find this change streamlines processing and boosts efficiency. While the release doesn't introduce new models or architectures, it enhances the runtime's performance across macOS, Linux, and Windows, including support for ROCm 7.2 and CUDA 12 and 13. This makes llama.cpp more efficient and adaptable for developers using different hardware configurations.