---
type: "raw_signal"
id: "the-upstream-ista-daslab-build-combines-gsq-and-625f58"
slug: "the-upstream-ista-daslab-build-combines-gsq-and-625f58"
title: "The upstream ISTA-DASLab build combines GSQ and RCO."
description: "ISTA-DASLab has published a GGUF quantized build of Qwen3.8-Flash-Next combining GSQ and RCO."
retrieval_nugget: "ISTA-DASLab has published a GGUF quantized build of Qwen3.8-Flash-Next combining GSQ and RCO."
observed_at: "2026-10-11"
record_date: "2026-10-11"
date_kind: "observed_at"
why_it_matters: "ISTA-DASLab has published a GGUF quantized build of Qwen3.8-Flash-Next combining GSQ and RCO. The source describes GSQ as learning grid assignments and per-group scales for each tensor through a Gumbel-Softmax relaxation. RCO selects a quantization type for each tensor while keeping the complete model within a size budget. The page also identifies the model as a mixture-of-experts architecture, ro"
novelty: "notable"
verification_level: "source-linked"
signal_type: "research"
source_platform: "huggingface.co"
topics: []
entities: ["ISTA-DASLab","Qwen3.8-Flash-Next","GSQ","RCO","GGUF"]
related_patterns: []
source_url: "https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF"
source_urls: ["https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:the-upstream-ista-daslab-build-combines-gsq-and-625f58"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/the-upstream-ista-daslab-build-combines-gsq-and-625f58/","markdown":"https://newruntime.com/signals/the-upstream-ista-daslab-build-combines-gsq-and-625f58.md","json":"https://newruntime.com/signals/the-upstream-ista-daslab-build-combines-gsq-and-625f58.json"}
---

# The upstream ISTA-DASLab build combines GSQ and RCO.

## Retrieval answer

ISTA-DASLab has published a GGUF quantized build of Qwen3.8-Flash-Next combining GSQ and RCO.

ISTA-DASLab has published a GGUF quantized build of Qwen3.8-Flash-Next combining GSQ and RCO. The source describes GSQ as learning grid assignments and per-group scales for each tensor through a Gumbel-Softmax relaxation. RCO selects a quantization type for each tensor while keeping the complete model within a size budget. The page also identifies the model as a mixture-of-experts architecture, routing tokens through selected expert feed-forward blocks rather than activating every expert for every token. The supplied source does not provide benchmark results, memory measurements, or deployment comparisons, so it establishes the build and its stated method, not a measured performance or quality advantage.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)