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
ClawBench
ClawBench

myllmbox/qwen38-flash-next-cluster-recipe

qwen38-flash-next recipe for tp=2 GB10

#LLM inference
Visit GitHub
Shell
129
16
2 contributors
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

ClawBench

a benchmark for personal agents

Momentum

How fast myllmbox/qwen38-flash-next-cluster-recipe 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 6 – Oct 22, 2026

Stars +125 in 47 days

0102030
21

Forks +16 in 47 days

024
4

Merged PRs 1 in 47 days

01
1

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

Top 25 in Shell

1911252519
Sep 6Sep 12Sep 18Sep 24Sep 30Oct 6Oct 12Oct 18
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
Sun, Sep 6, 2026+0+20Not trending
Mon, Sep 7, 2026+2+00Not trending
Tue, Sep 8, 2026+1+00Not trending
Wed, Sep 9, 2026+1+00Not trending
Thu, Sep 10, 2026+0+00Not trending
Fri, Sep 11, 2026+0+00Not trending
Sat, Sep 12, 2026+0+00Not trending
Sun, Sep 13, 2026+12+00#19
Mon, Sep 14, 2026+21+10#11
Tue, Sep 15, 2026+10+10Not trending
Wed, Sep 16, 2026+4+00Not trending
Thu, Sep 17, 2026+0+00Not trending
Fri, Sep 18, 2026+4+10Not trending
Sat, Sep 19, 2026+0+00Not trending
Sun, Sep 20, 2026+0+00Not trending
Mon, Sep 21, 2026+2+00Not trending
Tue, Sep 22, 2026+0+00Not trending
Wed, Sep 23, 2026+1+00Not trending
Thu, Sep 24, 2026+0+00Not trending
Fri, Sep 25, 2026+12+10#25
Sat, Sep 26, 2026+1+00Not trending
Sun, Sep 27, 2026+6+00Not trending
Mon, Sep 28, 2026+13+40#25
Tue, Sep 29, 2026+5+10Not trending
Wed, Sep 30, 2026+0+10Not trending
Thu, Oct 1, 2026+0+10Not trending
Fri, Oct 2, 2026+0+00Not trending
Sat, Oct 3, 2026+1+00Not trending
Sun, Oct 4, 2026+0+00Not trending
Mon, Oct 5, 2026+1+01Not trending
Tue, Oct 6, 2026+6+10Not trending
Wed, Oct 7, 2026+16+10#19
Thu, Oct 8, 2026+4+00Not trending
Fri, Oct 9, 2026+0+10Not trending
Sat, Oct 10, 2026+0+00Not trending
Sun, Oct 11, 2026+0+00Not trending
Mon, Oct 12, 2026+0+00Not trending
Tue, Oct 13, 2026+0+00Not trending
Wed, Oct 14, 2026+0+00Not trending
Thu, Oct 15, 2026+0+00Not trending
Fri, Oct 16, 2026+0+00Not trending
Sat, Oct 17, 2026+0+00Not trending
Sun, Oct 18, 2026+0+00Not trending
Mon, Oct 19, 2026+0+00Not trending
Tue, Oct 20, 2026+0+00Not trending
Wed, Oct 21, 2026+1+00Not trending
Thu, Oct 22, 2026+1+00Not trending
Total+125+161
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Mentions and achievements

Where people are talking about myllmbox/qwen38-flash-next-cluster-recipe, and every badge it has earned
  1. Oct 61 post

    • GLM 5.3 Flash EXL3 with TF @MiaAI_lab 레시피 Git Hub

      Read full on X, posted by @PlusTen_AI

      @PlusTen_AI · x.com

  2. 10 days earlier
  3. Sep 261 post

    • Whilst people are fawning over Opus 5.5, the local AI community kept cooking. @vr8vr8 recipe runs Qwen3.8-Flash-Next nearly twice as fast as the mainstream recipes on the same two Sparks. I ran my…

      Read full on X, posted by @yume_arasaki

      @yume_arasaki · x.com

  4. 19 days earlier
  5. Sep 71 post

    • Qwen 3.8 updated boost. 91.3 tok/s C1 code / 600.5 aggregate c16.

      Read full on X, posted by @softpoo

      @softpoo · x.com

  6. Sep 51 post

    • My friend kept nagging me to test Qwen 3.8 Flash-Next NVFP and I was hesitant since I was super happy with GLM 5.3 Flash but oh boy am I glad I put my agents to work. NVIDIA cooked with its own NVFP…

      Read full on X, posted by @softpoo

      @softpoo · x.com

You might also like

Repositories close to myllmbox/qwen38-flash-next-cluster-recipe
FeaturedAdvertise to 180K+ monthly visitors
ClawBench

a benchmark for personal agents

Busbar

Control what AI can do before it acts

Bifrost

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

myllmbox/qwen38-flash-next-recipe

Shell

qwen38-flash-next recipe for solo GB10

15610

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

Shell

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

29150

dime-online/qwen3.8-Flash-DGX-UltraFast

Python

Qwen3.8 Flash at 74 tok/s on a single DGX Spark / GB10. vLLM + MTP recipe, 212 tok/s at 8 streams.

766

blazux/qwen3.8-Flash-DGX

Python

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

46856

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

HTML

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

40958

0xBakeer/qwen38-flash-next-spark

Shell

Run Qwen3.8-Flash-Next (180B) on a single DGX Spark by keeping its 51B n-gram embedding table on NVMe

12512

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

Python

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

61492

tonyd2wild/Qwen3.8-Flash-Next-NVFP4-DGX-Spark

Python

Qwen3.8-Flash-Next (NVFP4) on DGX Spark in vLLM: one Spark 43.9 tok/s with our disk-backed n-gram table patch, staged gather and reduced-vocab MTP draft; TP2 SPEED 53.7; TP4 CONTEXT 9M KV pool. Launchers, patch, 40-prompt harness, KV ledger, credits. SGLang TP2 day-0 lane kept.

12918

styles01/sparkrun-recipes

Python

Custom inference recipes for NVIDIA DGX Spark — Qwen 122B DFlash hybrid

897