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
AxiomCode
AxiomCode
Bifrost
Bifrost
Busbar
Busbar

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

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

#LLM inference
Visit GitHub
Python
257
43
2 contributors
GNU Affero General Public License v3.0
website
FeaturedAdvertise to 180K+ monthly visitors
AxiomCode

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

Bifrost

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

Busbar

Control what AI can do before it acts

Momentum

How fast MiaAI-Lab/DeepSeek-v4.1-Flash-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

Sep 10 – Oct 19, 2026

Stars +235 in 40 days

0102030
26

Forks +43 in 40 days

0510
10

Merged PRs 6 in 40 days

012
2

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

Not in the Trendshift top 25 in this period

Sep 10Sep 15Sep 20Sep 25Sep 30Oct 5Oct 10Oct 15
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 PRs
Thu, Sep 10, 2026+0+00
Fri, Sep 11, 2026+26+100
Sat, Sep 12, 2026+22+50
Sun, Sep 13, 2026+9+00
Mon, Sep 14, 2026+25+20
Tue, Sep 15, 2026+18+21
Wed, Sep 16, 2026+4+20
Thu, Sep 17, 2026+7+01
Fri, Sep 18, 2026+7+10
Sat, Sep 19, 2026+7+02
Sun, Sep 20, 2026+5+10
Mon, Sep 21, 2026+2+10
Tue, Sep 22, 2026+1+10
Wed, Sep 23, 2026+4+20
Thu, Sep 24, 2026+11+01
Fri, Sep 25, 2026+7+11
Sat, Sep 26, 2026+12+30
Sun, Sep 27, 2026+10+20
Mon, Sep 28, 2026+3+10
Tue, Sep 29, 2026+6+00
Wed, Sep 30, 2026+1+00
Thu, Oct 1, 2026+1+00
Fri, Oct 2, 2026+1+20
Sat, Oct 3, 2026+3+10
Sun, Oct 4, 2026+2+00
Mon, Oct 5, 2026+1+20
Tue, Oct 6, 2026+2+00
Wed, Oct 7, 2026+0+00
Thu, Oct 8, 2026+0+00
Fri, Oct 9, 2026+4+00
Sat, Oct 10, 2026+1+20
Sun, Oct 11, 2026+2+00
Mon, Oct 12, 2026+1+00
Tue, Oct 13, 2026+0+00
Wed, Oct 14, 2026+2+00
Thu, Oct 15, 2026+0+00
Fri, Oct 16, 2026+2+00
Sat, Oct 17, 2026+10+10
Sun, Oct 18, 2026+7+00
Mon, Oct 19, 2026+9+10
Total+235+436
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Oct 141 post
    • The fastest way to run DeepSeek V4.1 Flash on two DGX Sparks just dropped, and it came from @sudoingX . 141 tok/s on structured output. Decode that stays flat from 8k to 240k context. The default…

      Read full on X, posted by @yume_arasaki

      @yume_arasaki · x.com

  2. 14 days earlier
  3. Sep 301 post
    • Four DGX Sparks, no switch, one prompt. DeepSeek V4.1 Flash built this football match in one shot. TP4 across all four nodes, wired as a ring over the QSFP ports. Reasoning on high, running in DSH,…

      Read full on X, posted by @DevRico003

      @DevRico003 · x.com

  4. 9 days earlier
  5. Sep 211 post
    • Simulated 5090 + 3 spark EXL3 Do consider Origjnal and pushing the limit of memory allocation on spark if your actually gonna use this configuration regularly … original quality is much faster…

      Read full on X, posted by @wrldsuksgo2mars

      @wrldsuksgo2mars · x.com

  6. 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

  7. 9 days earlier
  8. Sep 111 post2 posts
    • Yes you can get 69 tok/s on a single stream for a real agentic task. This is DeepSeek v4.1 Flash on 3x DGX Sparks

      Read full on X, posted by @MiaAI_lab

      @MiaAI_lab · x.com

    • One more thing... ⚡️ It comes with a TP=4 path, included Run DeepSeek v4.1 Flash on 4x DGX Sparks ✨ - 4M KV cache pool - 46 tok/s in prose single stream - 102 tok/s in prose in 4 concurrent streams -…

      Read full on X, posted by @MiaAI_lab

      @MiaAI_lab · x.com

You might also like

Repositories close to MiaAI-Lab/DeepSeek-v4.1-Flash-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/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark

Python

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

1.5k215

MiaAI-Lab/DeepSeek-v4-Flash-One-DGX-Spark

Python

DeepSeek v4 Flash EXL3 on one DGX Spark

34838

tonyd2wild/DeepSeek-v4-Flash-Vision-Exp-DSpark-1M-NVFP4-KV-2x-DGX-Spark

Python

DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark

49468

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

Python

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

27844

0xSero/deepseek-v4-flash-0731-spark-sparkinfer

Python

Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache

16619

raullenchai/twinspark

Shell

Production-grade recipe for DeepSeek-V4-Flash-0731 (284B MoE) on 2x NVIDIA DGX Spark: self-healing 2-node vLLM cluster, reboot-verified, tuned DSpark speculative decoding (~75 tok/s), full benchmarks, OpenAI Codex CLI integration

17620

Entrpi/ds4-on-spark

Shell

Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support

41032

maliubiao/dgx-spark-2-deepseek-flash-0731

Python

setup guide for deepseek-flash-0731 on two dgx-spark from scratch

26427

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

HTML

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

41157