AI Briefing#unsloth
The latest AI and developer news about #unsloth, with the original source and a short summary.
The latest AI and developer news about #unsloth, with the original source and a short summary.
Unsloth updated Qwen3.8-27B GGUFs with Dynamic V3.1 for 5-10% accuracy gains and introduced new 1-bit quantization types for the 2.4T parameter model.
New 2-bit to 6-bit quantizations achieve higher accuracy on agentic and coding benchmarks using 256K and 128K context windows.
The new quantization method reduces token usage by up to 50% and improves accuracy by 15% compared to other quants of the same size.
New quantization files improve accuracy by 10-15% on agentic benchmarks and introduce a new engram switching process for multiple precisions.
Unsloth reports its Dynamic 3.1 GGUFs for DeepSeek-V4.1 outperform GSQ-RCO by 10-20% on agentic tasks at 512K context, while statistical analysis suggests GSQ-RCO's claimed 99.80% recovery for IQ2_XXS is nearly impossible.
The update makes all of Cohere's latest model architectures compatible with llama.cpp and allows fine-tuning of Cohere Transcribe in Unsloth.
Presents a method for training and serving LLMs like Qwen3.5 by attaching decision heads to perform classification and judgment tasks
A community-developed Jinja template for GPT-OSS fixes a bug in the widely used Unsloth version that caused the model to drop final answers when reasoning traces were present in chat history.
Unsloth released the Qwen3.8-27B Dynamic 3.0 quantized model, improving accuracy.
Unsloth has released Dynamic v3.0 quantized models for Qwen3.8-27B, demonstrating improved accuracy.
Unsloth has launched the Desktop beta, integrating local model execution, training, and agent capabilities.
Unsloth has released the massive GGUF quantized files for Kimi K3.
Reasoning-Medical-27B, a model built on Qwen3.6-27B that maximizes medical reasoning ability, has been released.
Unsloth now officially supports local LLM inference and fine-tuning using AMD GPUs.
Unsloth has released NVFP4 quantized models for Qwen3.6 that boost inference speed by up to 2.5x on Blackwell GPUs.
Unsloth has released **MTP GGUF weights** for the 31B, 26B-A4B, and 12B models of Gemma 4.
Unsloth Studio now supports model training using MLX on Mac.
Unsloth has released GGUF versions of Qwen models with Multi-Token Prediction (MTP) technology applied.
A method for optimizing Qwen3.6 inference performance by grafting an MTP layer onto an Unsloth quantized model is introduced.
Unsloth collaborated with NVIDIA to boost LLM training speed by about 25%.
Unsloth fixed the Mistral Medium 3.5 inference bug and updated the GGUF.
Unsloth released a fixed version of the Mistral Medium 3.5 128B GGUF model that had been producing errors in long contexts.
Ran a Qwen3.6-27B UD-Q5_K_XL benchmark on an RTX 5090 with 19 runs and 93.9k tokens.
Mistral has released a unified multimodal model with 128B parameters and a 256k context.