PulseAugur
EN
LIVE 16:41:15
ENTITY ISTA-DASLab

ISTA-DASLab

PulseAugur coverage of ISTA-DASLab — every cluster mentioning ISTA-DASLab across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
8
9 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
0
0 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

5 day(s) with sentiment data

RECENT · PAGE 1/1 · 9 TOTAL
  1. COMMENTARY · CL_345949 ·

    Benchmark dispute erupts over ISTA-DASLab's gsq-rco quant performance

    A controversy has emerged regarding benchmark results published by ISTA-DASLab for their gsq-rco quants. Unsloth has criticized ISTA-DASLab for not disclosing their methodology, making it difficult to reproduce the quot…

  2. TOOL · CL_345738 ·

    Local LLMs surge with Qwen, Unsloth, and Strata innovations

    The local Large Language Model (LLM) landscape is experiencing rapid advancement, particularly in Q4 2026. Innovations in quantization by Unsloth and ISTA-DASLab are making powerful models like Qwen Flash-Next and Qwen-…

  3. SIGNIFICANT · CL_337502 ·

    DeepSeek-V4.1-Flash-1017 compressed to 1-bit with expert pruning

    ISTA-DASLab has released a specialized version of the DeepSeek-V4.1-Flash-1017 model, named GSQ-RCO Coder. This model is a 763B parameter mixture-of-experts architecture that has been significantly compressed by removin…

  4. TOOL · CL_320333 ·

    Underdog Saluki 27B: A guide to running a quantized Qwen3.8-27B model

    This tutorial details how to run the Underdog Saluki 27B model, a quantized version of Qwen3.8-27B. Saluki is noted for maintaining tool-calling capabilities at a reduced size and reportedly outperforms the full model o…

  5. TOOL · CL_318911 ·

    Hugging Face releases Granite Switch 4.1.1 with faster model updates · 2 sources tracked

    Hugging Face has released Granite Switch 4.1.1, a patch update to its modular language model architecture. This update includes an improved multilingual Granite Speech ASR model with native punctuation and capitalizatio…

  6. TOOL · CL_310472 ·

    Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF model updated with new expert selection

    An updated version of the Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF model has been released. This update modifies the selection of retained experts, with approximately 25% of the expert choices differing from the previous r…

  7. TOOL · CL_290046 ·

    Underdog releases 2-bit Saluki 27B model, outperforming Qwen3.8-27B in tool calling

    Underdog, a research initiative from Conway Research, has released Saluki 27B, a highly compressed 2-bit version of the Qwen3.8-27B model. This new model, available under the Apache 2.0 license, significantly reduces th…

  8. TOOL · CL_292696 ·

    Qwen3.8-Flash-Next model quantized with Strata control vector released

    A new repository on Hugging Face offers quantized versions of the Qwen3.8-Flash-Next model, specifically focusing on the GSQ-RCO quantizations developed by the Deep Algorithms and Systems Lab at ISTA. This release inclu…

  9. TOOL · CL_278148 ·

    Strata project enables large local LLM execution on consumer GPUs

    The Strata project enables running large language models like Qwen3.8-Flash-Next locally on consumer hardware, including GPUs with 12GB VRAM. It achieves this by distributing the model's workload across the GPU, CPU, RA…