Update: next checkpoint has effectively reached Jev calibration parity on MMLU! Also 8…
This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
Update: next checkpoint has effectively reached Jev calibration parity on MMLU! Also 8 bit quant is looking good and should fit in ~30gb memory locally!
Posted by Archer (3.3k followers) 1 days ago · 25 likes · 2.4k views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- Testing small models for personal agent efficacy is fun- especially when you're doing it… — @PaulGugAI
- Local Hermes status feed said “Context window grown” mid-session — not an error. Starts… — @MichaelGannotti
- Meet w8a8_dynamic_asym-e2e: a Llama model squeezed into 8-bit precision. Why care? It… — @HuggingModels
- Really cool that MiMo V2.6 has an official Distill-Qwen-9B variant remind me of the… — @victormustar
- Runs the 2.78-trillion-parameter Kimi K3 model on a single CPU using 8 GB of RAM without… — @tom_doerr
- open weight models just crossed another line — @EHuanglu
- Xiaomi just dropped Mimo 2.6 Pro which claims to be the best open source model. I played… — @deedydas
- I wanted to run difficult agentic benchmarks with MiMo v2.6 Distill, like DeepSWE and… — @bnjmn_marie
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 41.4k posts from 5k X accounts over the last 14 days, 1.7k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 11:47 UTC. Full method.