Strata runs Qwen3.8-Flash-Next on a 12GB gaming PC
Niko1221/Strata streams a ~125B-parameter MoE from RAM and SSD into a 12GB consumer GPU and serves it as a local OpenAI-/Anthropic-compatible API.
Mistral opens a public preview of Mistral Large 4, a 1.05T-parameter open-weight model trained in Europe
Mistral puts Mistral Large 4 ("le Chonk") into public preview: a 1.05T-parameter open-weight MoE served from EU datacenters, with weights promised by month's end.
Cohere North Small Translate: 218B MoE translation model
Cohere's first North-family translation model is a 218B/25B-active MoE under CC BY-NC 4.0. Cohere-run WMT26 tests score it 83.6; the eval method is GPT-5.6-Sol as judge.
Meta Muse Glimmer 30B: Apache agentic multimodal model
Meta's Muse Glimmer is a 30B Apache-2.0 multimodal model distilled from Muse Spark that fits a 24GB consumer GPU with 4-bit quantization. Architecture, benchmarks, and DFlash.
Moonshot AI Kimi K3: 2.8T open-weights MoE model
Kimi K3 is a 2.8T-parameter open-weights MoE model built on Kimi Delta Attention and Attention Residuals, with 1M-token context and native vision. Weights to follow by July 27.
DiffusionGemma: 1,000+ tokens/sec open-weights text gen
Google DeepMind's June 10, 2026 release: a 26B/3.8B text-diffusion model denoising 256 tokens in parallel; ~4x faster than AR on a single H100, Apache 2.0, explicitly experimental.