Xiaomi quietly ships a Qwen-based 9B model claimed to be the best in its class, MIT-licensed and runnable on 8GB RAM
solyarisoftware · x · 2026-09-25
@itsPaulAi highlights a quietly released Xiaomi model built on Qwen-9B, calling it the best 9B model available. Key points:
- MIT license, fully open for commercial use
- Multimodal: image + text input
- Solid performance on coding and agentic tasks
- Runs locally on as little as 8GB of memory, including laptops with unified memory
A notable new option for local and offline small-model deployments.
More from Models
- Ex-OpenAI researcher launches System One Models: Jev makes typed decisions in 70-500ms — JeremyCMorgan · 2026-09-25
- OpenAI to preview GPT-6 Cyber model and first-of-its-kind security product, per Fortune — jeremyakahn · 2026-09-25
- Vision model tier list updated with Opus 5.5, GPT-6 Sol/Luna, and Grok 4.7 — ducha_aiki · 2026-09-25
- Anthropic Accused of Quietly Nerfing Models Weeks After Launch, Opus 5.5 Expected to Follow — iannuttall · 2026-09-25
- TypeSafe AI launches Jev, a 'System One' model for bounded decisions in agent runs — hardimanjames · 2026-09-25
- Qwen Flash Next IQ4_XS beats 27B FP8 on MMLU-Pro, GPQA and GSM8K in community eval — smallDeltaBigEffect · 2026-09-25