QuantTrio Shrinks Alibaba's Qwen3.6 From 70 GB to 24 GB for Workstation Deployment
QuantTrio shipped a 4-bit AWQ quantization of Qwen3.6-35B-A3B that compresses the MoE down to roughly 24GiB for vLLM deployment.
20 stories
QuantTrio shipped a 4-bit AWQ quantization of Qwen3.6-35B-A3B that compresses the MoE down to roughly 24GiB for vLLM deployment.
Krea opens the beta for a new frontier image editing model that completes 2K edits in under 8 seconds at roughly a third of competitor pricing.
NVIDIA's new open 120B mixture-of-experts model fuses text, image, document, and video reasoning into one agent-ready backbone with 12B active parameters.
OpenBMB's MiniCPM-V 4.7 packs 35B parameters into a mixture-of-experts vision model that runs on an iPhone at 13+ tokens per second.
Mistral's first time-series foundation model family hits #1 on three major forecasting benchmarks with just 209M parameters and runs on CPU.
How prompt injection exploits trust boundaries through saved memory, and what runtime checks can prevent unsafe actions.
Sakana AI released The Agentic Scientist, an open-source scaffold that wraps coding agents like Claude Code and Codex into a rigorous end-to-end research loop.
GVHMR recovers world-grounded 3D human motion from a single video using gravity-aligned coordinates, processing 45 seconds of footage in 280 ms.
Anthropic is paying PhDs up to $167K for four months to turn their domain expertise into training data and evaluations for Claude.
Sarvam's new MCP lets your coding agent spin up Indian-language voice bots, dial contact lists, and pull call analytics without leaving the IDE.
A tiny Python harness lets Claude Code or Codex drive a real iPhone through macOS iPhone Mirroring, or any Android over adb, with no jailbreak and nothing installed on the phone.
A new reinforcement learning reward treats chain-of-thought as gradient descent, cutting tokens by about 50% while boosting accuracy on math, science, and code benchmarks.
A 315M-parameter Japanese embedding model built on ModernBERT-Ja tops JMTEB benchmarks while handling 8K context, outperforming OpenAI and billion-parameter rivals.
A 31B Gemma 4 fine-tune turns open language models into fast, calibrated decision engines for routing, extraction and classification in Polish and English.
vLLM-Omni now serves Fish Audio's 35B directable TTS model with 128 concurrent streams on one H200 and 255 ms median time to first audio.
IFM's new Arabic-first model family spans 0.9B to 375B parameters, with a flagship MoE that matches Claude Sonnet 5 on Arabic benchmarks and acts as an agent.
A training-free sparse attention method uses a handful of representative attention heads as proxies, delivering 10.3x attention speedup on long contexts.
TypeSafe AI ships Jev 1.14 with image inputs, a bounding box primitive, and 4x longer context, all behind opt-in danger zone headers.
Pi Agent Desktop wraps the open-source Pi coding agent in a native Mac, Windows, and Linux app with signed auto-updates and no CLI setup.
Thinking Machines rolled out Dimuon, a LoRA-specific optimizer that beats AdamW on step count in supervised fine-tuning while leaving RL mostly unchanged.