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

kindlingai/glm-5.3-flash-gx10

GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.

#LLM inference
Visit GitHub
Python
90
15
2 contributors
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 kindlingai/glm-5.3-flash-gx10 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 +92 in 47 days

01020
17

Forks +15 in 47 days

0123
3

Merged PRs 67 in 47 days

01020
18

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

Not in the Trendshift top 25 in this period

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 PRs
Sun, Sep 6, 2026+0+00
Mon, Sep 7, 2026+1+00
Tue, Sep 8, 2026+0+00
Wed, Sep 9, 2026+0+00
Thu, Sep 10, 2026+0+00
Fri, Sep 11, 2026+0+00
Sat, Sep 12, 2026+0+00
Sun, Sep 13, 2026+0+00
Mon, Sep 14, 2026+0+00
Tue, Sep 15, 2026+0+00
Wed, Sep 16, 2026+0+00
Thu, Sep 17, 2026+0+00
Fri, Sep 18, 2026+0+00
Sat, Sep 19, 2026+0+00
Sun, Sep 20, 2026+0+00
Mon, Sep 21, 2026+0+00
Tue, Sep 22, 2026+0+00
Wed, Sep 23, 2026+0+00
Thu, Sep 24, 2026+1+00
Fri, Sep 25, 2026+0+10
Sat, Sep 26, 2026+0+02
Sun, Sep 27, 2026+0+00
Mon, Sep 28, 2026+6+17
Tue, Sep 29, 2026+17+218
Wed, Sep 30, 2026+16+313
Thu, Oct 1, 2026+14+210
Fri, Oct 2, 2026+7+12
Sat, Oct 3, 2026+3+20
Sun, Oct 4, 2026+2+00
Mon, Oct 5, 2026+5+00
Tue, Oct 6, 2026+2+00
Wed, Oct 7, 2026+1+00
Thu, Oct 8, 2026+2+00
Fri, Oct 9, 2026+1+00
Sat, Oct 10, 2026+0+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+1+04
Tue, Oct 13, 2026+1+10
Wed, Oct 14, 2026+4+00
Thu, Oct 15, 2026+0+00
Fri, Oct 16, 2026+2+27
Sat, Oct 17, 2026+4+00
Sun, Oct 18, 2026+0+00
Mon, Oct 19, 2026+0+02
Tue, Oct 20, 2026+1+02
Wed, Oct 21, 2026+1+00
Thu, Oct 22, 2026+0+00
Total+92+1567
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Oct 21 post

    • 用SVG画一只骑自行车的鹈鹕沿着海岸线兜风，加入踩踏、车轮转动等动画细节，做成20帧循环，可直接打开的HTML，支持暂停、重播和倍速"。 按照这个部署不知道是不是exl3量化问题，得到结果并不理想

      Read full on X, posted by @0411_1986

      @0411_1986 · x.com

  2. Sep 301 post

    • Oof, the PRs have measurements for every change, but it's hard to say with these numbers. There's a lot of novel work here for adaptive-k dflash (responsible for a lot of the decode), the custom RDMA…

      Read full on X, posted by @mmastrac

      @mmastrac · x.com

  3. 23 days earlier
  4. Sep 71 post

    • Been running ~50-70 tok/s successfully here on NVFP4 with TP=4. I don't recommend EXL3 - it takes a longer to reason through harder problems. RedHatAI's weights have been stellar for me.

      Read full on X, posted by @mmastrac

      @mmastrac · x.com

You might also like

Repositories close to kindlingai/glm-5.3-flash-gx10
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

alexellis/glm-5.3-flash-4x-dgx-spark-switchless

Shell

GLM-5.3-Flash (NVFP4) at TP4 across 4x DGX Spark via a switchless RoCE ring + DFlash2 — reproducible recipe

1078

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

Python

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

47591

Morrowmake/glm53-flash-cmp170hx-recipe

Python

GLM-5.3-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 482.6 tok/s single-user, up to 943.7 tok/s at 8 users, 262K context, TP4 or PP4, one-command container install

8311

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

Python

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

737146

tonyd2wild/GLM-5.3-Flash-NVFP4-DFlash2-2x-DGX-Spark

Python

GLM-5.3-Flash (NVFP4) on 2x NVIDIA DGX Spark - vLLM TP2, 262K context, MTP. World-first deploy recipe: 7 day-0 bugs found and fixed, patched sm121 image, probes and full report.

23727

sybil-solutions/glm-flash-lite

Python

GLM-5.3-Flash EXL3 on one 24 GB RTX 3090 + DDR4: elastic GPU expert cache, zero-copy experts, AVX2 CPU tier, OpenAI API

32135

MiaAI-Lab/GLM-5.3-Flash-NVFP4-Dual-DGX-Spark

Shell

2x DGX Spark recipe for LibertAIDAI/GLM-5.3-Flash-NVFP4 (NVFP4, Ray TP=2, multimodal)

9011

jayleaton/glm53-tensorfold-spark

Python

GLM-5.3-Flash (abliterated EXL3) on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8x faster decode than vLLM, 4x256k concurrent threads, byte-exact speculative decoding. Work in progress.

11712

yhfgyyf/vllm-deepseek-v4-sm89

Python

Run DeepSeek-V4.1-Flash / DeepSeek-V4-Flash and GLM-5.3-Flash on SM89 (Ada / RTX 4090) and SM120 (RTX PRO 6000) with vLLM

19324