deepseek-v4.1-flash-1017-gsq-rco-gguf
deepseek-v4.1-flash-1017-gsq-rco-gguf is We’re on a journey to advance and democratize artificial intelligence through open source and open science.. It is ranked #139 on the Dev Radar, in Other, first seen 6 days ago and shared in 7 posts (263.4k views).
ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF · Hugging Face Hugging Face Log In Sign Up ISTA-DASLab / DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF Like 65 Follow IST Austria Distributed Algorithms and Systems Lab 2.24k Text Generation GGUF gsq rco quantization mixed-precision ist-daslab Mixture of Experts deepseek arxiv: 2604.18556 arxiv: 2605.00649 License: mit Model card Files Files and versions xet Community 4 Deploy Copy to bucket new DeepSeek-V4.1-Flash-1017 · GSQ-RCO GGUFs Non-uniform GGUF quantizations of a 763B-parameter, 384-expert MoE, produced with GSQ and RCO . Overview This repository provides GGUF quantizations of…
What people said about deepseek-v4.1-flash-1017-gsq-rco-gguf on X
🔥牛逼了！12GB显卡本地跑763B！DeepSeek-V4.1-Flash-1017量化版炸裂登场，前沿质量几乎零损失！ ISTA-DASLab团队发布GSQ-RCO非均匀量化版，Strata引擎原生支持。763B参数MoE大模型最低压到1.75 bpw，在消费级硬件上就能跑！ 核心亮点 🔹极致压缩 + 几乎无损：IQ2_XXS（2.00 bpw，约249GB）在AIME25、GPQA-Diamond、LiveCodeBench v6上100%恢复原始模型分数；IQ1_M（1.75 bpw，约231GB）整体恢复98.7%。 🔹真正本地可行：单张12GB显卡 +…
— @NFT_Chen, 6 days ago · 1.7k likes · see the post
🚨卧槽Strata升级啦！DeepSeek V4.1-Flash-1017 在 Strata 0.2.6 上速度直接翻倍！ 一张 16G 消费级显卡 + 大内存，本地跑 763B 参数模型，从“勉强能聊”变成“日常完全够用”。 实测对比（RTX 4080 Super 16G + 128G DDR4 · IQ2_XXS · 8K 上下文） 🔹生成速度：旧版约 10 t/s → 新版 16.7–22.7 t/s（翻倍以上） 🔹Prefill：旧版约 4 t/s → 新版 8–22 t/s 🔹显存占用 15.4G，缓存 853 个专家，内存约 107G，日常聊天流畅无压力 官方大内存优化（专家全载入 RAM） 🔹1×…
— @NFT_Chen, 5 days ago · 343 likes · see the post
Local AIのみんな、もう一度お知らせ！ StrataがDeepSeek-V4.1-Flash-1017に対応しました！ @mchelcig からGSQ-RSO quantsもすでに出ています！ 12GB VRAM + 64GB DDR5 RAMでも、SSDにEngramを置けば、すべてのquantsを動かせます！ これからテストして、MayaとMaya quantsの結果を比較してみます！ お楽しみに！
— @ItsmeAjayKV, 6 days ago · 307 likes · see the post
Alternatives to deepseek-v4.1-flash-1017-gsq-rco-gguf
- Step-5-Preview — Join the countdown
- Google — Argon is rolling out today to Google Ultra and Pro subscribers in the @GeminiApp and Search, and Ultra subscribers in…
- nanbeige4.3-33b — We’re on a journey to advance and democratize artificial intelligence through open source and open science.
- Spark-X2.5 — Healthcare-focused AI just got a little lighter. Same powerful reasoning, less memory to worry about. 🤖
- anymove — Open source
- Ideogram — Live in Ideogram and the API
deepseek-v4.1-flash-1017-gsq-rco-gguf in numbers
- Rank on the Dev Radar: #139 of 8801
- Shared in 7 posts by 2 accounts: @NFT_Chen, @ItsmeAjayKV
- 263.4k views on those posts
- First seen 6 days ago, last shared 3 days ago
- Pricing seen by AGK Intelligence: open source
- Market: Other
FAQ
What is deepseek-v4.1-flash-1017-gsq-rco-gguf?
We’re on a journey to advance and democratize artificial intelligence through open source and open science. It was first shared on X 6 days ago and is ranked #139 on the Dev Radar.
Is deepseek-v4.1-flash-1017-gsq-rco-gguf free?
It is open source.
Who shared deepseek-v4.1-flash-1017-gsq-rco-gguf?
2 accounts on X, including @NFT_Chen, @ItsmeAjayKV, in 7 posts totalling 263.4k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 21:12 UTC. Full method.