Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Busbar
Busbar
Bifrost
Bifrost
AxiomCode
AxiomCode

MiaAI-Lab/Qwen3.8-Flash-Next-Dual-DGX-Sparks

Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark

#LLM inference
Visit GitHub
HTML
411
57
2 contributors
GNU Affero General Public License v3.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Busbar

Control what AI can do before it acts

Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

AxiomCode

Give Al Agents a Deeper Understanding of Your Codebase with a Code Graph

Momentum

How fast MiaAI-Lab/Qwen3.8-Flash-Next-Dual-DGX-Sparks is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Aug 26 – Oct 19, 2026

Stars +298 in 55 days

0102030
30

Forks +57 in 55 days

0510
10

Merged PRs 20 in 55 days

0246
5

Trendshift Trendingwhere the repository ranked each day it made the top 25

Top 25 in Shell

171615
Aug 26Sep 2Sep 9Sep 16Sep 23Sep 30Oct 7Oct 14
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRsShell
Wed, Aug 26, 2026+0+31Not trending
Thu, Aug 27, 2026+13+102Not trending
Fri, Aug 28, 2026+29+45#17
Sat, Aug 29, 2026+21+40#16
Sun, Aug 30, 2026+17+30Not trending
Mon, Aug 31, 2026+30+10#15
Tue, Sep 1, 2026+18+00Not trending
Wed, Sep 2, 2026+9+10Not trending
Thu, Sep 3, 2026+9+10Not trending
Fri, Sep 4, 2026+6+11Not trending
Sat, Sep 5, 2026+6+10Not trending
Sun, Sep 6, 2026+13+40Not trending
Mon, Sep 7, 2026+7+30Not trending
Tue, Sep 8, 2026+14+13Not trending
Wed, Sep 9, 2026+7+21Not trending
Thu, Sep 10, 2026+4+00Not trending
Fri, Sep 11, 2026+5+30Not trending
Sat, Sep 12, 2026+4+10Not trending
Sun, Sep 13, 2026+0+10Not trending
Mon, Sep 14, 2026+11+10Not trending
Tue, Sep 15, 2026+3+00Not trending
Wed, Sep 16, 2026+5+14Not trending
Thu, Sep 17, 2026+7+00Not trending
Fri, Sep 18, 2026+3+10Not trending
Sat, Sep 19, 2026+5+10Not trending
Sun, Sep 20, 2026+3+00Not trending
Mon, Sep 21, 2026+7+20Not trending
Tue, Sep 22, 2026+4+00Not trending
Wed, Sep 23, 2026+3+00Not trending
Thu, Sep 24, 2026+4+00Not trending
Fri, Sep 25, 2026+2+10Not trending
Sat, Sep 26, 2026+4+12Not trending
Sun, Sep 27, 2026+3+00Not trending
Mon, Sep 28, 2026+1+00Not trending
Tue, Sep 29, 2026+2+01Not trending
Wed, Sep 30, 2026+1+10Not trending
Thu, Oct 1, 2026+0+00Not trending
Fri, Oct 2, 2026+0+20Not trending
Sat, Oct 3, 2026+0+00Not trending
Sun, Oct 4, 2026+2+00Not trending
Mon, Oct 5, 2026+1+00Not trending
Tue, Oct 6, 2026+4+00Not trending
Wed, Oct 7, 2026+2+10Not trending
Thu, Oct 8, 2026+1+00Not trending
Fri, Oct 9, 2026+0+00Not trending
Sat, Oct 10, 2026+2+00Not trending
Sun, Oct 11, 2026+0+00Not trending
Mon, Oct 12, 2026+0+00Not trending
Tue, Oct 13, 2026+2+00Not trending
Wed, Oct 14, 2026+0+10Not trending
Thu, Oct 15, 2026+1+00Not trending
Fri, Oct 16, 2026+2+00Not trending
Sat, Oct 17, 2026+0+00Not trending
Sun, Oct 18, 2026+1+00Not trending
Mon, Oct 19, 2026+0+00Not trending
Total+298+5720
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Mentions and achievements

Where people are talking about MiaAI-Lab/Qwen3.8-Flash-Next-Dual-DGX-Sparks, and every badge it has earned
  1. Oct 31 post

    • MiaAI_lab blocked me, and I'm not the only one. I'm not here for drama. I spent today checking everything I'd heard against git history, commits and posts, and threw out whatever didn't hold up. This…

      Read full on X, posted by @Jonnykov

      @Jonnykov · x.com

  2. 13 days earlier
  3. Sep 201 post

    • I get a lot of data on what people actually run on their Sparks. Here’s what I have: Solo DGX Spark - Most run Qwen3.8 Flash Next 2x DGX Sparks - GLM 5.3 Flash or DeepSeek v4.1 Flash 3x DGX Sparks,…

      Read full on X, posted by @MiaAI_lab

      @MiaAI_lab · x.com

  4. Sep 161 post

    • Qwen3.8-Flash-Next for 2x DGX Sparks just got better - Increased decode tok/s across the board - Lots of PRs merged, issues resolved Full details 👇

      Read full on X, posted by @MiaAI_lab

      @MiaAI_lab · x.com

  5. 7 days earlier
  6. Sep 91 post

    • 难得的不是让两台 DGX Spark 跑起 Qwen3.8，而是把“能启动”补成可维护的双机推理方案。 它用 vLLM 的 TP2+EP+MTP3，补齐 PLE、MXFP8 和 FP8 KV 兼容问题，并提供 GPU 占用预检、权重校验、离线验证及 rsync/NFS 分发。默认 FP8 KV 实测约 365 万 token。代价也明确：每节点需约 126 GiB 磁盘，NFS…

      Read full on X, posted by @vintcessun

      @vintcessun · x.com

  7. Sep 61 post2 posts

    • One spark: Two sparks:

      Read full on X, posted by @rwojo

      @rwojo · x.com

    • So should I run Qwen 3.8 Flash Next on 1x or 2x Sparks? Dual recipe is about 10% faster than single, but can do concurrency of 8 (vs 4) and 2x the aggregate at max. KV cache also goes to 3.78M from…

      Read full on X, posted by @rwojo

      @rwojo · x.com

  8. 8 days earlier
  9. Aug 291 post

    • 用两台 DGX Spark 张量并行跑 176B NVFP4 量化 MoE，一条命令完成下载、镜像构建和集群启动；顺带补齐了上游 SGLang 在 SM121 上缺的稀疏注意力内核和 NVFP4 KV cache。

      Read full on X, posted by @QingQ77

      @QingQ77 · x.com

  10. Aug 272 posts

    • Qwen 3.8 Flash on 2x DGX Spark right now. I'm blown away by this one. It feels like the model I've been chasing since the days when we experienced Openclaw, when Opus was actually good. Mac Studio M5…

      Read full on X, posted by @yume_arasaki

      @yume_arasaki · x.com

    • So far definitely feeling this, and it feels like the intelligence makes it feel even faster than it is as I’ve seen fewer broken tool calls and reasoning loops so far compared to DeepSeek v4f.…

      Read full on X, posted by @sethforprivacy

      @sethforprivacy · x.com

You might also like

Repositories close to MiaAI-Lab/Qwen3.8-Flash-Next-Dual-DGX-Sparks
FeaturedAdvertise to 180K+ monthly visitors
AxiomCode

Give Al Agents a Deeper Understanding of Your Codebase with a Code Graph

Busbar

Control what AI can do before it acts

Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold

Shell

Qwen3.8 Flash Next on one DGX Spark (TensorFold)

27744

MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark

Python

Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)

60991

blazux/qwen3.8-Flash-DGX

Python

recipe for running Qwen3.8-Flash-Next on a single DGX Spark

46354

MiaAI-Lab/DeepSeek-v4.1-Flash-DGX-Sparks

Python

DeepSeek-V4.1-Flash on 3-4x NVIDIA DGX Sparks

25642

MiaAI-Lab/Qwen3.8-27B-SGLang-DGX-Spark

Shell

Qwen3.8 27B on SGLang for DGX Spark

47461

MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark

Python

DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks

1.5k215

MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold

Python

GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold

46187

MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks

Python

DeepSeek v4.1 Flash EXL3 2.9 bpw for 2x DGX Sparks

27744

MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks

Python

GLM-5.3 Flash EXL3 for 2-4x DGX Sparks

736145