LIVE
Study measures how coding agents pick third-party tools03/09/26|OpenAI's GPT-6 Astra sets new state-of-the-art on ARC-AGI-303/09/26 · OpenAI|ESPO: A Prompt Optimization Method That Beats GEPA With Shorter, More Stable Prompts03/09/26|"Last Translation Benchmark": a large-scale collaborative effort for a definitive MT benchmark03/09/26|NVIDIA pushes local AI at IFA 2026 with RTX Spark PCs and a personal inference router03/09/26 · NVIDIA|Google DeepMind unveils WeatherNext 3, its most accurate weather AI model yet03/09/26 · Google DeepMind|OpenAI Launches $1B Daybreak Program for Frontline Cybersecurity Defenders03/09/26 · OpenAI|Hcompany releases NeoMME, a compact multimodal-native encoder for retrieval03/09/26 · Hcompany|Playco cuts manual fixes by 50% using GPT-6 Astra for prototyping03/09/26 · OpenAI|Legora reviews 41 financial documents in minutes with GPT-6 Astra03/09/26 · OpenAI|Hugging Face open-sources a project training a coding model to paint watercolours03/09/26 · Hugging Face|A 350M-Parameter Model Improved in 100 GRPO Steps for Better Structured Outputs03/09/26|Study measures how coding agents pick third-party tools03/09/26|OpenAI's GPT-6 Astra sets new state-of-the-art on ARC-AGI-303/09/26 · OpenAI|ESPO: A Prompt Optimization Method That Beats GEPA With Shorter, More Stable Prompts03/09/26|"Last Translation Benchmark": a large-scale collaborative effort for a definitive MT benchmark03/09/26|NVIDIA pushes local AI at IFA 2026 with RTX Spark PCs and a personal inference router03/09/26 · NVIDIA|Google DeepMind unveils WeatherNext 3, its most accurate weather AI model yet03/09/26 · Google DeepMind|OpenAI Launches $1B Daybreak Program for Frontline Cybersecurity Defenders03/09/26 · OpenAI|Hcompany releases NeoMME, a compact multimodal-native encoder for retrieval03/09/26 · Hcompany|Playco cuts manual fixes by 50% using GPT-6 Astra for prototyping03/09/26 · OpenAI|Legora reviews 41 financial documents in minutes with GPT-6 Astra03/09/26 · OpenAI|Hugging Face open-sources a project training a coding model to paint watercolours03/09/26 · Hugging Face|A 350M-Parameter Model Improved in 100 GRPO Steps for Better Structured Outputs03/09/26|
8 Go

Best local LLM for a laptop (8 GB)

Small models that run on a laptop with no dedicated GPU, in Q4, within 8 GB of RAM. Not benchmark champions, but good enough to summarise, rewrite, classify and answer offline.

#ModelArena EloRAM (Q4)HostingLicence
1🇺🇸Gemma 3n E4B
Google
13177 GoSelf-hostablegemma
2🇺🇸Granite 4.1 8B
IBM
13067 GoSelf-hostableapache-2.0
3🇺🇸Gemma 3 4B
Google
13035 GoSelf-hostablegemma
4🇫🇷Ministral 8B
Mistral AI
12377 GoSelf-hostablemistral-research
5🇺🇸Llama 3.1 8B
Meta
12117 GoSelf-hostablellama-3.1-community
6🇺🇸Llama 3.2 3B
Meta
11664 GoSelf-hostablellama-3.2-community
7🇺🇸Llama 3.2 1B
Meta
11113 GoSelf-hostablellama-3.2-community
8🇫🇷Mistral 7B
Mistral AI
11107 GoSelf-hostableapache-2.0
9🇨🇳Qwen3 0.6B
Alibaba
2 GoSelf-hostableapache-2.0
10🇨🇳Qwen3 8B
Alibaba
7 GoSelf-hostableapache-2.0
Data verified on 4 September 2026Open in the comparator

Method

Deterministic ranking on comparator data: LMArena Elo (style control) first, HuggingFace downloads second for models without an Elo. Prices and licences are verified at the official source and dated. No model is ranked by an LLM.

Other guides