9B model
PulseAugur coverage of 9B model — every cluster mentioning 9B model across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Anthropic red team shows AI models running on cheap hardware
Anthropic's red team demonstrated a 26B parameter model running on 15 Android TV boxes at a speed of 0.39 tokens per second. Additionally, a 9B parameter model successfully established its own inference server and repli…
-
How to run local AI models on older hardware
Running large language models locally on older or less powerful hardware requires careful selection of model size and quantization to ensure usability. Smaller models, such as 7B to 9B parameter models with Q4 quantizat…
-
Perplexity releases new embedding models, achieves SOTA on benchmarks
Perplexity has released two new late-interaction embedding models, pplx-embed-v2-late, which can retrieve text, images, and pages within a shared embedding space. These models achieve frontier performance and are availa…
-
New SRIM method enhances image protection against malicious edits
Researchers have developed a new method called SRIM to protect images from malicious editing, particularly when the images are resized. Existing methods are optimized for specific resolutions, but SRIM accounts for unkn…
-
Developer seeks interest for open-source 9.4B parameter dense LLM
An independent developer is seeking community interest for a 9.4 billion parameter dense language model they have developed. The model incorporates advanced techniques like Moonshot's AttnRes modeling and RoPE/NoPE laye…
-
Agentic DJ uses Ollama and 9B model for local music streaming
A developer has created an agentic DJ using the Ollama platform and a 9B model to play music from a personal library. The system utilizes tools for searching music, checking schedules, and accessing weather data to sele…
-
Researcher replaces paid API with self-hosted 9B model via knowledge distillation
A researcher details how they replaced a paid API with a self-hosted 9-billion parameter model using a multi-teacher knowledge distillation technique. This method, inspired by a 2015 paper by Geoffrey Hinton, allowed th…