FunctionGemma is a specialized version of our Gemma 3 270M model fine-tuned for function calling.
Gemma 4: Byte for byte, the most capable open models
Gemma 4: our most intelligent open models to date, purpose-built for advanced reasoning and agentic workflows.
Gemma 3n model overview | Google AI for Developers
Gemma 3n is a generative AI model optimized for use in everyday devices, such as phones, laptops, and tablets. This model includes innovations in parameter-efficient processing, including Per-Layer Embedding (PLE) parameter caching and a MatFormer model architecture that provides the flexibility to reduce compute and memory requirements. These models feature audio input handling, as well as text and visual data.
Function calling | OpenAI API
Learn how function calling enables large language models to connect to external data and systems.
TranslateGemma: A new suite of open translation models
TranslateGemma is a new family of open translation models built on Gemma 3.
Inference Time Memory Module | Research | Tiles
Simple inference-time memory module that treats memory management as a series of LLM calls and agent loops over a markdown-based file tree.
Berkeley Function Calling Leaderboard (BFCL) V4
Explore The Berkeley Function Calling Leaderboard (also called The Berkeley Tool Calling Leaderboard) to see the LLM's ability to call functions (aka tools) accurately.
Principal type-schemes for functional programs | Proceedings of the 9th ACM SIGPLAN-SIGACT symposium on Principles of programming languages
As part of the Digital Library's transition to Open Access, new features for researchers are available in the Premium Edition. Click here to learn more.
gemma3n
Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.
On-Device LLM Throughput Calculator - a Hugging Face Space by FL33TW00D-HF
This tool estimates and visualizes the throughput of Large Language Models on devices with memory bandwidth constraints. Users input device and model configurations, and the tool generates a plot s...
Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency
We’re releasing Gemma 4 quantization-aware training checkpoints, reducing memory requirements and improving on-device performance.
Benchmarks | EXO
Transparent benchmarks for LLMs tested on real hardware. Coming soon.
Muse Glimmer: Meta’s 30B Model Built for Efficient Inference
Inside Meta’s 30B local reasoning model and its tiny KV cache
CompactLTJ: Space & Time Efficient Leapfrog Triejoin on Graph Databases
Leapfrog Triejoin (LTJ) is arguably the most practical and popular worst-case-optimal (wco) algorithm for solving basic graph patterns in graph databases. Its main drawback is that it needs the database triples (subject, predicate, object) represented as paths in a trie, for each of the six orders of subject, predicate, and object. The resulting blowup in space makes most systems disregard LTJ or implement it only partially, which makes their corresponding algorithms non-wco. In this paper we show that, by using compact data structures, it is possible to build an index that at the same time matches the query time performance of the fastest classic wco index, and uses a fraction of the space of non-wco indices (which are much slower). Concretely, we make use of compact tree representations to store functional tries using one bit per trie edge, instead of one pointer, and further reduce the space by storing partial tries. Our most compact variant uses 5–6 times less space than classic wco implementations and 2–3 times less than classic non-wco systems. At solving queries, it is on par with the fastest classic wco system, and 30–40 times faster than non-wco systems. We further incorporate improved query resolution strategies into CompactLTJ variants, which makes it considerably faster than classic wco systems as well, on queries that do not output too many results. Finally, we show how CompactLTJ can incorporate dynamism without altering its performance, even under very demanding update regimes. We leave a public fully-functional implementation of CompactLTJ that can be directly used by practitioners.
