GGUF replaces bitsandbytes for low-VRAM LoRA training on local hardware
New techniques enable training massive Qwen and DeepSeek models in limited VRAM using GGUF base formats, eliminating the need for CPU offloading on specific hardware.
Results for “qwen”
Daily coverage of AI, developer tools and infrastructure. Each story explains what happened and why it matters, with a link to the original source.
Microsoft launches Decision-1 model on Qwen base to rival OpenAI and TypeSafe
Microsoft released Microsoft-Decision-1 in Foundry, built on Alibaba’s Qwen3.5-9B, matching competitor pricing while omitting image support and open weights.
Open-source FPGA accelerator runs modern LLMs with full toolchain
The openTPU project releases a complete AI accelerator design in one repository, running models like Qwen3 and LFM2.5 on a Kintex-7 FPGA card with bit-exact simulation.
Fine-tuning search agents with multi-turn reinforcement learning on SageMaker
Amazon demonstrates how multi-turn RL fine-tunes a Qwen3.6-27B search agent, cutting failure rates from 22% to under 1% while improving retrieval quality.
Bespoke Labs releases Nimble, a fast 9B decision model for local inference
Bespoke Labs has released Nimble, an open-weight 9B decision model fine-tuned from Qwen3.5-9B that provides probabilistic answers to structured questions in under 100ms on local hardware.
Optimizing long-context embedding inference on Cloud TPU with vLLM
Google details how native TPU support in vLLM enables elastic scaling and high-precision embedding inference for Qwen3 models.
