I finally found an open-source local LLM that actually competes with cloud AI
…It's under Apache 2.0, which is a bigger deal than it sounds - previous Gemma releases had Google's own restrictive terms attached, so this was the first time you could…
Search
Related topics:
Google Gemma
All sources
xda-developers.com
27
developer.nvidia.com
17
blogs.nvidia.com
11
screenrant.com
8
androidauthority.com
6
huggingface.co
6
amd.com
6
android-developers.googleblog.com
5
wccftech.com
4
techpowerup.com
4
engadget.com
3
arstechnica.com
3
Tracked topic
Google Gemma
Gemma is a family of open-weight language models released by Google for text generation and related NLP tasks.
Top stories
Google's Gemma 4 finally made me care about running local LLMs
…You can run Gemma 4 models on your phone or laptop for free It's easier than you think As I just mentioned above, Gemma 4 models have been intentionally engineered to…
I ran a powerful local AI model on my laptop, and it didn’t feel like a compromise
…But the recent release of Google DeepMind’s Gemma 4 12B challenges that status quo. This 12-billion-parameter mid-sized model handles multi-step reasoning and a massive (and efficient) 256K…
AMD's GAIA Defaults To Better Model, Continued Improvements For Local AI
…With GAIA 0.17.5, they have replaced Qwen 3.5 35B with Gemma 4 E4B as the default model. They explained their rationale in the release announcement as: "Gemma 4 E4B…
Discussions and forums
Gemma 4 MTP released
Blog post: https://blog.google/innovation-and-ai/technology/developers-tools/multi-token-prediction-gemma-4/ MTP draft models: https://huggingface.co/google/gemma-4-31B-it-assistant https://huggingface.co/google/gemma-4-…
google/gemma-4-12B · Hugging Face
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-w…
Show HN: Run Agent Skills with mistral.rs v0.8.10: /v1/skills support and more
Hey all! I'm the maintainer of mistral.rs. I just landed support for OpenAI-compatible Agent Skills via a /v1/skills endpoint, and it works with local open models.Until now Skills have basically been locked to closed mod…
20
2
The Qwen 3.6 35B A3B hype is real!!!
My personal test for small local LLM intelligence is to check whether a model has any ability to understand the code that I write for my own academic research. My research is on some pretty niche topics and I doubt that …
TextGen is now a native desktop app. Open-source alternative to LM Studio (formerly text-generation-webui).
Hi all, I have been making a lot of updates to my project, and I wanted to share them here. TextGen (previously text-generation-webui, also known as my username oobabooga or ooba) has been in development since December 2…
Google's Gemma 4 isn't the smartest local LLM I've run, but it's the one I reach for most
…What makes Gemma 4 different from previous open-weight releases is the sheer range of what Google shipped. There are four models in the family, all built from the same Gemini 3…
I put Google's Gemma 4 on my homelab and Tailscale on my phone — and cancelled Claude Pro
…The next step was to select the best Gemma 4 model for my PC, based on my mobile usage. The Gemma 4:26b was overkill and wouldn't fit in 12GB VRAM…
Lemonade 10.1 Released For Latest Improvements For Local LLMs On AMD GPUs & NPUs
…Additionally, Lemonade 10,1 now supports Gemma 4 models on GPUs. Downloads and more details on today's Lemonade 10.1 release via GitHub . In addition to the open-source code there…
I replaced the expensive Gemini AI Pro subscription with these local models, and my productivity didn't drop a bit
…for a cleaner home screen Gemma 4 E2B and 26B A4B Gemma is essentially the open-weight sibling of Gemini , and with the release of Gemma 4, the performance gap has practically…
I turned my phone into a local LLM server, and it handles vision, voice, and tool calls
…You do need to compile from master and not a tagged release, though, as support for Gemma 4 E4B's audio is pretty recent. Gemma 4 E4B itself takes a bit more…
I ran Gemma 4 (26B) on a 10-year-old-GPU, and it's reliable enough to replace the cloud
…Finally, I executed cmake -B build -DGGML_VULKAN=ON and cmake --build build --config Release -j$(nproc) to build the tool, which took around 4–5 minutes. Gemma-4-26B-A4B works…