Products
Developers
About

Insights & Information

Find what you need to accelerate your AI journey

Blog

SambaNova Cloud Launches the Fastest DeepSeek-R1 671B: Sign Up for Early Access

DeepSeek-R1, the best open source reasoning model in the market, is now available on SambaNova Cloud for Dedicated...

Blog

SambaNova Cloud Developer Tier is Live

The SambaNova Cloud Developer Tier will allow you to pay for token consumption for higher rate limits on the most...

Blog

Now On SambaNova Cloud, Tülu 3 405B, A New Model Better than DeepSeek V3

We are excited to announce the addition of Tülu 3 405B, a fine tune of Llama 405B that performs better than DeepSeek...

Blog

Hugging Face Partners with SambaNova to Supercharge its Inference API Capabilities

Available now, Hugging Face developers can take advantage of the lightning fast inference speeds made possible with...

Blog

Unlock the Future of Multi-Agent AI Workflows with CrewAI and SambaNova

To accelerate the adoption of agentic AI, SambaNova is announcing the integration of the CrewAI agentic framework...

Blog

Test-Time Compute Available on SambaNova Cloud with Qwen QwQ-32B-Preview

Available now, developers have access to the best open source test-time compute model released by Alibaba:...

Blog

Meta Llama 3.3 70B Now Available Today for Developers and Enterprises

Available now, SambaNova has optimized and released Meta's Llama 3.3 70B model on its RDU hardware architecture.

Blog

The SambaNova Startup Accelerator: Helping AI Innovators Realize Their Vision

The SambaNova Startup Accelerator program is designed not just to support, but to partner with startups as they...

Blog

Qwen 2.5 32B-Coder Available on SambaNova Cloud - 5X Faster than GPUs

Available on SambaNova Cloud, developers now have access to some of the best open-source models in the Qwen 2.5...

Blog

Hugging Face Makes it Faster to Review Papers with SambaNova

With our recent partnership with Hugging Face, we have built a new tool to make this process significantly more...

Blog

How Gradio Makes Building Apps on SambaNova Cloud Super Easy

Working together, we’ve created a SambaNova-Gradio integration that can be used to build and deploy AI apps using...

Blog

Zilliz: Powering AI RAG Applications with Vector Embeddings

SambaNova is working with Zilliz, a cloud-native software company, to showcase the power of combining fast inference...

Blog

Outperforming GPT-4o with Llama 3 8B: Domain Specific Fine Tuning for RAG

An end-to-end solution leveraging open-source LLMs to generate a Q&A dataset for fine-tuning smaller and faster...

Blog

Correcting Common AI Benchmarking Errors with AI Starter Kits

The Benchmarking AI Starter Kit offers functionality to evaluate different LLMs available on SambaStudio or...

Blog

Accelerating Coding with SambaNova Cloud

In this post, we demonstrate a useful and practical application of the SambaNova Cloud to power Continue, the...

Blog

Developer Tips: Creating Valuable AI

In this post, we explore the strategic considerations and decision-making processes that can help you create...

Blog

Judging Judges: All that is LLM Judgements does not glitter

An examination of where LLM-as-a-Judge can satisfyingly act as a judge of an outer model's performance and where it...

Blog

Replacing the Judge: Can Llama 405B Outperform GPT4 in the Court of AI?

While LLM-as-a-Judge offers a favorable alternative to human evaluations, closed source LLMs impose some limitations...

Blog

Advanced AI Apps Need Fast Inference. SambaNova Cloud Delivers It

By improving inference performance, SambaNova has unlocked the full potential of Llama 3.1 405B and enabled...

Blog

Why SambaNova's SN40L Chip is The Best for Inference

Comparing the end-user inference performance of SambaNova's technology against that of Groq and Cerebras.

Blog

SubgoalXL: Pushing the Boundaries of LLM in Formal Theorem Proving

SubgoalXL represents a significant step forward in the field of AI-powered theorem proving.

Blog

Does reduced precision hurt? A bit about losing bits.

Recent work highlighted how quantization for recent LLaMa 3 models can lead to non-negligible decay in model...

Blog

NAIRR; Govt-funded AI Research Resources

NAIRR pilot, in partnership with SambaNova, provides generative AI platforms for groundbreaking academic research....

Blog

Tokens Per Second is Not All You Need

In this post, we explore why tokens per second doesn't paint the full picture of enterprise LLM inference...