blorg

cd ls cd ls….

Okay this one is insane. A new 18B frankenstein model was just released on @huggingface — Beats the new Qwen3.6-35B-A3B on a 44-test suite despite requiring 12GB VRAM instead of 24GB 🤯 Runs on a SINGLE RTX 3060 (!) 🧠 Opus 4.6 & GLM-5.1 reasoning in one model ⚡️ 66+ tok/s stable on mid-range GPUs 🧪 Experimental, no additional training 🛠️ Perfect tool calling & agentic reasoning 📷 Fits on low hardware, any 12gb card 📚 GGUF size is 9.8GB (Q4_K_M) Another gift from Jackrong, adding both qwopus and glm-distilled qwen together was not on my bingo card. Truly seems like the sweet spot between 9B and 27B models right now. The ultimate model for 12-16GB VRAM owners? huggingface.co/Jackrong/Qwopu…

@0xSero people with 8gb looking at shit like this on social media

I am not worried about losing my subscriptions anymore :p

@bclavie amazing looking benchmarks!! is this Open-Source?

I'm so excited to introduce this! We've worked on a million different moving parts to produce this. I'm fairly confident it's the best multimodal model that exists, period -- and it's not too shabby at pushing back the LIMITs of retrieval either...

@junthekey @XiaomiMiMo @openclaw @opencode @kilocode @cline @roocode what's your estimate of conversion between Xiaomi's Credits and actual tokens?

@XiaomiMiMo @openclaw @opencode @kilocode @cline @roocode Boss Lei, I'm mifans. Hello, how are you? I just spent 1 day with MimoV2 Pro with very light usage. model is good, but the plan is not sufficient.

Xiaomi MiMo Token Plan is here. One subscription. All modalities. Build with MiMo-V2-Pro, Omni, and TTS. No 5-hour limits. No throttling. Transparent usage and billing. Just ship. Works with whatever you use: @openclaw, @opencode, @kilocode, @cline, @roocode Includes priority beta access to our newest models. 12% off your first purchase. TTS is free for now. Subscribe now → platform.xiaomimimo.com

Hi @Ferrari, Can I have a free Ferrari now?

Today we’re announcing Ternary Bonsai: Top intelligence at 1.58 bits Using ternary weights {-1, 0, +1}, we built a family of models that are 9x smaller than their 16-bit counterparts while outperforming most models in their respective parameter classes on standard benchmarks. We’re open-sourcing the models under the Apache 2.0 license in three sizes: 8B (1.75 GB), 4B (0.86 GB), and 1.7B (0.37 GB).

Touching grass isnt enough i need to connect to the mycelium network

@Cesioz @LesNews underrated comment

@LesNews The batteries after a few cycles...

Le constructeur chinois BYD présentant une recharge aussi rapide qu’un plein d’essence

a workaround for this is if you run third-party harnesses like OpenClaw inside TempleOS, the power of HolyC and God forbids Anthropic from blocking your claude subscription (it's an exception in their Terms of Service) but it does make your opus act a little weird though...

If you like @OurWorldInData's data visualization and use @OpenWebUI, boyyyyyy I made the right plugin for you. Check it out here: github.com/matifema/OWDTo… ⭐️