Gemma 4

Google's family of small open-weight models with quantization-aware variants.

OtherAI & MLopen-weightssmall-modelsllmlocal-inferenceembeddingsopen-weightlocal-models

Recommended in 3 threads

Amazon saves millions by replacing Sonnet 4.6 with Strands Decider
strandsagents.com · 3 days ago
One commenter replaced LLM pipelines with Gemma embeddings plus a classifier head.
Upload Your RAM
uploadyourram.org · 6 days ago
Offered as proof that offline local AI meaningfully changes what a disconnected machine can do.
Anthropic IPO buyers see valuation as low as $1.1T
bloomberg.com · 7 days ago
Small QAT versions handle everyday questions well on modest hardware.

Gemma ↗AI & ML
Google's family of open-weight language models that can run locally.
3 threads
Gemma 4 31B AI & ML
An open-weight language model from Google.
1 thread
GLiNER ↗AI & ML
A family of compact models for promptable entity extraction and classification.
1 thread
Qwen ↗AI & ML
Alibaba's family of open-weight large language models.
9 threads
IBM Granite ↗AI & ML
IBM's family of language models reportedly trained on legally obtained data.
1 thread
MiniCPM ↗AI & ML
A family of small open-weight language models aimed at edge devices.
1 thread
GLM ↗AI & ML
An open-weights large language model family from Zhipu AI.
11 threads
Qwen 3.8 ↗AI & ML
A family of open weight language models from Alibaba.
1 thread

OpenRouter ↗
A marketplace that routes API requests to many LLM inference providers.
19 threads
DeepSeek ↗
A family of large language models offered via a low-cost API.
12 threads
llama.cpp ↗
A C/C++ engine for running LLMs locally.
12 threads
GLM ↗
An open-weights large language model family from Zhipu AI.
11 threads
Qwen ↗
Alibaba's family of open-weight large language models.
9 threads
DeepSeek V4.1 Flash ↗
A low-cost DeepSeek language model available via API.
8 threads
Artificial Analysis ↗
A site benchmarking and comparing AI models on quality, price and speed.
7 threads
Claude ↗
Anthropic's AI model and command-line assistant.
7 threads
Qwen 3.8 Flash Next ↗
A Qwen open-weight model that can be run locally.
5 threads
Strata ↗
An open-source project for running large MoE models on small-VRAM GPUs with system RAM.
5 threads
OpenCode Go ↗
A subscription plan for accessing models through the OpenCode coding tool.
4 threads
Pangram ↗
A service that uses a trained model to detect AI-generated text.
4 threads