Open-Weight LLM Showdown Week 7: Mistral Small 4 Impresses but Stays Out of Reach
Mistral Small 4's 119B MoE unifies reasoning, vision, and coding—but needs datacenter hardware. Qwen 3.5 35B-A3B remains the consumer GPU king at 112 t/s.
Category
Local AI
Open Source AI Wins: China Overtakes US in Downloads, Robotics Explodes, and Hugging Face Hits 2 Million Models
Hugging Face's Spring 2026 report reveals China now leads in AI model downloads, robotics datasets jumped 2,200%, and open-weight models are achieving 10x-1000x cost advantages.
Mistral's Voxtral TTS: Open-Weight Voice Cloning That Challenges ElevenLabs
Mistral releases a 4B parameter text-to-speech model that clones voices from 3 seconds of audio, runs locally on 16GB GPUs, and beats ElevenLabs in human evaluations.
Open-Weight LLM Showdown Week 6: MiMo-V2-Flash Brings 309B Parameters to Consumer GPUs
MiMo-V2-Flash runs 309B parameters on RTX 4090s. GLM-5 sets benchmarks but needs datacenters. Llama 4 Scout stays out of reach.
Google's TurboQuant Could Let You Run Bigger AI Models on Your Hardware
New compression algorithm achieves 6x memory reduction with zero accuracy loss. No retraining required. This matters for anyone running local AI.
Open Source AI Wins: NVIDIA Goes Local-First, OpenAI Returns to Its Roots, Qwen 3.5 Beats Models 13x Its Size
NVIDIA's Nemotron 3 Super runs agents locally, OpenAI releases Apache 2.0 models for the first time since GPT-2, and Alibaba's 9B parameter model outperforms 120B competitors.
Open-Weight LLM Showdown Week 5: Qwen 3.5 Dominates, Nemotron 3 Super Redefines Efficiency
Qwen 3.5's MoE models hit S-tier benchmarks, NVIDIA's Nemotron 3 Super delivers 5x throughput gains, and GLM-4.7-Flash brings frontier coding to consumer GPUs. The open-weight race just accelerated.
MiroThinker 72B: The Open-Source Research Agent That Outperforms GPT-5
An open-source AI agent using interactive scaling beats OpenAI's GPT-5-high on Humanity's Last Exam. Here's what makes it different.
Open-Source AI Wins: OpenAI Goes Apache 2.0, Superpowers Hits 94K Stars, and Xiaomi Reveals Its Secret Model
This week's open-source highlights: GPT-OSS marks OpenAI's first open weights since GPT-2, Superpowers becomes the most-starred AI coding framework, and Hunter Alpha was Xiaomi all along.
Open-Weight LLM Showdown: GTC Pivots to Inference, DeepSeek V4 Still MIA
Jensen Huang bets on inference chips, Ollama adds multimodal support, and DeepSeek V4 remains the most anticipated release that hasn't happened yet.
Open-Weight LLM Showdown: Mistral Small 4 Arrives, DeepSeek V4 Finally Lands
Mistral drops a 119B MoE model under Apache 2.0, DeepSeek V4 emerges from stealth, and dual RTX 5090 setups are matching H100 on 70B inference. This week changed the game.
Open-Source AI Wins: NVIDIA Goes All-In on Open Models, Lightricks Ships 4K Video, and Local Inference Matures
GTC 2026's biggest announcements were open-source. Nemotron 3 Super runs locally on RTX PCs, LTX 2.3 generates 4K video with audio, and vLLM hits production grade.
ByteDance's DeerFlow 2.0: Run Your Own AI Agent Team Locally
TikTok's parent company just open-sourced a powerful framework for running coordinated AI agents on your own hardware. Here's what it does and how to set it up.
Best Local AI Agent Models: Tool Use by GPU Tier (August 2026)
Which local models can actually use tools, call functions, and run multi-step workflows? Function-calling and TAU-bench picks from 8GB to 32GB VRAM.
Best Local Chat Models by VRAM Tier (August 2026)
Head-to-head comparison of local chat and assistant models from 8GB to 32GB VRAM. Current picks: Qwen3.5, Gemma 4, GPT-OSS, Qwen3.6, and GLM-4.7-Flash.
Best Local Coding Models by VRAM Tier (August 2026)
Which open-weight coding model to run locally? HumanEval and SWE-bench picks from 8GB to 32GB GPUs. Qwen2.5-Coder, Qwen3.6, Devstral, KAT-Coder.
Best Local Speech Models by VRAM Tier (August 2026)
Local TTS and STT by VRAM tier: Parakeet, Canary, MOSS-Transcribe-Diarize, Step-Audio-EditX, Fish Audio S2 Pro and Kokoro, and the licence each ships.
Best Local Models for Translation: Every VRAM Tier (August 2026)
TranslateGemma, NLLB-200, Aya Expanse and Qwen3.5 by VRAM tier, with the licence terms that decide whether you can ship what you run.
Best Local Vision Models: Every GPU Tier (August 2026)
Local image analysis, OCR, and visual reasoning from 8GB to 32GB VRAM. Qwen3.5 replaces Qwen3-VL at most tiers, and 16GB stays unresolved.
llama.cpp Joins Hugging Face: What It Means for Local AI's Future
Georgi Gerganov's team is now at Hugging Face, unifying the model hub with the inference engine that powers Ollama, LM Studio, and the entire local AI ecosystem.
12GB VRAM: Every AI Task You Can Run Locally (August 2026)
Local AI on a 12GB GPU: chat, coding, vision, speech and agents for RTX 3060 12GB or RTX 4070. Current picks, per-quant weight sizes, honest limits.
16GB VRAM: Every AI Task You Can Run Locally (August 2026)
Local AI on a 16GB GPU: chat, coding, translation, speech and agents for RTX 4060 Ti, RTX 5060 or Arc A770, and why the vision tier stays unresolved.
24GB VRAM: Every AI Task You Can Run Locally (August 2026)
Local AI on a 24GB GPU: chat, coding, vision, speech and agents for RTX 3090 or RTX 4090. Current picks, per-quant weight sizes, and an open runtime bug.
8GB VRAM: Every AI Task You Can Run Locally (August 2026)
Local AI on an 8GB GPU: chat, coding, vision, speech and agents for RTX 4060 or RTX 3070. Current picks, named quantisations, honest limits.