@teortaxesTex: Holy crap, a Brazil municipal employee has discovered a 1000x faster way to finetune LLMs – with a little weird trick! …
Summary
A municipal employee in Brazil claims to have discovered a method that makes LLM fine-tuning 1000x faster, though analysis suggests the resulting model, Rio 3.5, is essentially a mixture of existing open-source models Nex N2 Pro and Qwen 3.5.
View Cached Full Text
Cached at: 06/15/26, 03:06 PM
Holy crap, a Brazil municipal employee has discovered a 1000x faster way to finetune LLMs – with a little weird trick! This is insane. Global South rising… Frontier labs hate him https://t.co/x95d5EZNfg
Nex (@NexEcosystem): The Rio 3.5 model broke the internet this week. The plot twist? It’s essentially our open-source model, Nex N2 Pro, wearing a different hat.
🤯 We analyzed the weights, and the recipe is exact: Rio 3.5 ≈ 0.6 * Nex N2 Pro + 0.4 * Qwen 3.5
It even literally introduces itself
Similar Articles
Good results fine tuning a local LLM like Qwen 3:0.6B to categorize questions
A developer fine-tunes a small Qwen 3 0.6B model using the Unsloth framework to categorize household questions, achieving good results with only 850 training examples.
@tom_doerr: Fine-tunes LLMs with a no-code GUI https://github.com/h2oai/h2o-llmstudio…
H2O LLM Studio is an open-source framework and no-code GUI that simplifies the fine-tuning of large language models, supporting techniques like LoRA, DPO, and integration with Hugging Face.
@TeksEdge: Holy ! New King of the Open Source LLMs! Beats Leading OS Models. Time to start testing to verify benchmarks. Nex-N2-Pr…
Nex-N2-Pro, a new open-source LLM from NexEcosystem, reportedly outperforms leading models like Kimi-K2.6 and DeepSeek-V4-Pro on benchmarks, featuring adaptive and coherent thinking.
@DivyanshT91162: Local LLMs just hit a whole new level This Hugging Face release is actually insane: "gpt-oss-20b-tq3" An official 20B+ …
A new 20B+ parameter MoE model from OpenAI, quantized to 3-bit via TurboQuant and optimized with MLX, allows for high-performance local LLM inference on standard 16GB MacBooks.
@songjunkr: SuperQwen3.6-35B-DFlash-MLX is ready. Benchmark: Comparison of original vs. tuned versions on 100 actual items from com…
A fine-tuned 35B-parameter Qwen model optimized for MLX shows benchmark gains on GPQA Diamond, MMLU-Pro, IFEval, HumanEval+ and MBPP+ and ships without censorship.