Battle 2 of my AI tournament! ⚔️
This is a AI post classified by AGK Intelligence as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
Battle 2 of my AI tournament! ⚔️ RTX 5090 vs RTX 5060 Ti, 32GB against 16GB. Hardware Cup, semifinal 2. The winner meets the winner of semifinal 1 in tonight's final. RTX 5090, 32 GB: Qwen3.8-27B, NVFP4 NInfer, MTP3 drafts RTX 5060 Ti, 16 GB: Qwen3.8-27B, EXL3 2.5 bpw Mia's 16 GB kit (ExLlamaV3 1.6.0), MTP drafts The same model, same game, one attempt, no help. The 16 GB card runs a smaller quant. Different engines per card, so one match is a game, not a benchmark. NInfer and its model file by @neroued, with NVFP4 weights from @unslothai. Kit by @MiaAI_lab. EXL3 quant and ExLlamaV3 by
Posted by Niklas (2.9k followers) 51 min ago · 1 likes · 123 views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- You can now Run Uncensored DeepSeek-V4-Pro-Qwen3.5-9B locally on a 5 GB Laptop with zero… — @0x0SojalSec
- You can run locally Uncensored "DeepSeek-V4-Pro-Qwen3.5-9B" 5.6GB. — @0x0SojalSec
- Meet the Qwen3.8-27B Ultimate Heretic Uncensored Turbo Brilliance 50x AGI NEO GGUF. It's… — @HuggingModels
- Comparing Ameriqwen against Alibaba Qwen — @slimer48484
- Meet Mirage, a new image-text-to-text model from Cactus-Compute. It handles object… — @HuggingModels
- What did you do when local models weren't restricted? — @thepirateface
- 💥炸了！本地跑Qwen 3.8新巅峰！tqLLM 1.4.4碾压TensorFold/Strata/Splash，27B & Flash-Next速度起飞，Qwen… — @NFT_Chen
- Meet Arete-27B: a fine-tuned Qwen3.5 model built for value alignment and rich… — @HuggingModels
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.2k posts from 5k X accounts over the last 14 days, 10.6k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 21:15 UTC. Full method.