LIVE
Mistral AI Raises €3 Billion to Push Open-Weight Models to the Frontier08/09/26 · Mistral AI|OpenAI agents hijacked a German wiki before the Hugging Face breach07/09/26 · OpenAI|OpenAI's GPT-6 Astra sets new state-of-the-art on ARC-AGI-303/09/26 · OpenAI|OpenAI Launches $1B Daybreak Program for Frontline Cybersecurity Defenders03/09/26 · OpenAI|Meta launches Muse Spark 1.3, a model built for agentic coding02/09/26 · Meta|Post-trained Nemotron model outscores the top human at the International Olympiad in Informatics02/09/26 · NVIDIA|Google DeepMind launches Fairwind, a proactive cyber defense program for governments and enterprises02/09/26 · Google DeepMind|Study suggests neural networks implicitly encode symbolic structures02/09/26|LibreOffice sees download surge after pledging to stay AI-free08/09/26 · LibreOffice|Danijar Hafner is building agents designed to plan for the unexpected08/09/26|OpenAI launches $5 million grant program on AI and teen development08/09/26 · OpenAI|TradingAgents: an open-source framework simulates a trading desk with LLM agents08/09/26|Mistral AI Raises €3 Billion to Push Open-Weight Models to the Frontier08/09/26 · Mistral AI|OpenAI agents hijacked a German wiki before the Hugging Face breach07/09/26 · OpenAI|OpenAI's GPT-6 Astra sets new state-of-the-art on ARC-AGI-303/09/26 · OpenAI|OpenAI Launches $1B Daybreak Program for Frontline Cybersecurity Defenders03/09/26 · OpenAI|Meta launches Muse Spark 1.3, a model built for agentic coding02/09/26 · Meta|Post-trained Nemotron model outscores the top human at the International Olympiad in Informatics02/09/26 · NVIDIA|Google DeepMind launches Fairwind, a proactive cyber defense program for governments and enterprises02/09/26 · Google DeepMind|Study suggests neural networks implicitly encode symbolic structures02/09/26|LibreOffice sees download surge after pledging to stay AI-free08/09/26 · LibreOffice|Danijar Hafner is building agents designed to plan for the unexpected08/09/26|OpenAI launches $5 million grant program on AI and teen development08/09/26 · OpenAI|TradingAgents: an open-source framework simulates a trading desk with LLM agents08/09/26|
Hardware Match

Which model for Laptop 8 Go RAM?

6 GB usable for the model (80% of RAM, CPU execution). 30 open-weight models fit in memory.

The margin goes to context: count ~1 GB per 8k tokens for a 7B model. A small margin means a short context.

ModelEloQuantizationRAM requiredMarginSpeedRun
Gemma 3 4BGoogle · 4B1303Q4_K_M5 Go+1 Goslow (CPU) ollama run gemma3:4b
Llama 3.2 3BMeta · 3.21B1166Q8_06 Go+0 Goslow (CPU) ollama run llama3.2:3b
Llama 3.2 1BMeta · 1.24B1111FP165 Go+1 Goslow (CPU) ollama run llama3.2:1b
Kokoro-82MHexgrad · 0.08BFP162 Go+4 Goslow (CPU)Hugging Face ↗
ChatterboxResemble AI · 0.5BFP163 Go+3 Goslow (CPU)Hugging Face ↗
Parakeet TDT 0.6B v3NVIDIA · 0.6BFP163 Go+3 Goslow (CPU)Hugging Face ↗
Qwen3 0.6BAlibaba · 0.6BFP163 Go+3 Goslow (CPU) ollama run qwen3:0.6b
TripoSRStability AI · 0.5BFP163 Go+3 Goslow (CPU)Hugging Face ↗
Gemma 3 1BGoogle · 1BFP164 Go+2 Goslow (CPU) ollama run gemma3:1b
Phi-4 MiniMicrosoft · 3.8BQ4_K_M4 Go+2 Goslow (CPU) ollama run phi4-mini
Stable Fast 3DStability AI · 1BFP164 Go+2 Goslow (CPU)Hugging Face ↗
CogVideoX 5BZhipu AI · 5BQ4_K_M5 Go+1 Goslow (CPU)Hugging Face ↗
FLUX.2 [klein] 4BBlack Forest Labs · 4BQ4_K_M5 Go+1 Goslow (CPU)Hugging Face ↗
Gemma 4 E4BGoogle · 4BQ4_K_M5 Go+1 Goslow (CPU)Hugging Face ↗
Qwen3 4BAlibaba · 4.02BQ4_K_M5 Go+1 Goslow (CPU) ollama run qwen3:4b
TRELLISMicrosoft · 1.2BFP165 Go+1 Goslow (CPU)Hugging Face ↗
TRELLIS.2Microsoft · 4BQ4_K_M5 Go+1 Goslow (CPU)Hugging Face ↗
Wan 2.2 5BAlibaba · 5BQ4_K_M5 Go+1 Goslow (CPU)Hugging Face ↗
Whisper large-v3OpenAI · 1.55BFP165 Go+1 Goslow (CPU)Hugging Face ↗
Dia 1.6BNari Labs · 1.6BFP166 Go+0 Goslow (CPU)Hugging Face ↗
Gemma 4 E2BGoogle · 2BFP166 Go+0 Goslow (CPU)Hugging Face ↗
Granite 4.1 3BIBM · 3BQ8_06 Go+0 Goslow (CPU)Hugging Face ↗
Hunyuan3D 2.1Tencent · 3BQ8_06 Go+0 Goslow (CPU)Hugging Face ↗
Lucie 7BOpenLLM France · 6.7BQ4_K_M6 Go+0 Goslow (CPU)Hugging Face ↗
Ministral 3 3BMistral AI · 3BQ8_06 Go+0 Goslow (CPU)Hugging Face ↗
OLMo 3 7BAllen AI · 7BQ4_K_M6 Go+0 Goslow (CPU)Hugging Face ↗
Orpheus 3BCanopy Labs · 3BQ8_06 Go+0 Goslow (CPU)Hugging Face ↗
SmolLM3 3BHugging Face · 3.1BQ8_06 Go+0 Goslow (CPU)Hugging Face ↗
Voxtral Mini 3BMistral AI · 3BQ8_06 Go+0 Goslow (CPU)Hugging Face ↗
Z-Image TurboAlibaba · 6BQ4_K_M6 Go+0 Goslow (CPU)Hugging Face ↗