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
Bifrost
Bifrost
AxiomCode
AxiomCode
Busbar
Busbar

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

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

#LLM inference
Visit GitHub
Python
463
89
2 contributors
Apache License 2.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
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

Busbar

Control what AI can do before it acts

Momentum

How fast MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold 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 30 – Oct 19, 2026

Stars +405 in 20 days

050100
70

Forks +89 in 20 days

01020
18

Merged PRs 58 in 20 days

051015
13

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

Top 25 in Shell

47111919
Sep 30Oct 3Oct 6Oct 9Oct 12Oct 15Oct 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
Wed, Sep 30, 2026+0+00Not trending
Thu, Oct 1, 2026+70+115#4
Fri, Oct 2, 2026+48+186#7
Sat, Oct 3, 2026+39+143#11
Sun, Oct 4, 2026+23+42#19
Mon, Oct 5, 2026+19+85Not trending
Tue, Oct 6, 2026+16+35Not trending
Wed, Oct 7, 2026+21+40Not trending
Thu, Oct 8, 2026+33+39#19
Fri, Oct 9, 2026+20+21Not trending
Sat, Oct 10, 2026+16+413Not trending
Sun, Oct 11, 2026+15+20Not trending
Mon, Oct 12, 2026+16+21Not trending
Tue, Oct 13, 2026+17+30Not trending
Wed, Oct 14, 2026+10+30Not trending
Thu, Oct 15, 2026+6+20Not trending
Fri, Oct 16, 2026+15+23Not trending
Sat, Oct 17, 2026+8+21Not trending
Sun, Oct 18, 2026+11+14Not trending
Mon, Oct 19, 2026+2+10Not trending
Total+405+8958
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Mentions and achievements

Where people are talking about MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold, and every badge it has earned
    1. Oct 141 post

      • 7/ Is mine dumber? Unknown. His experts are FP4 weights and activations, with 8-bit dense layers and BF16 KV. Mine are EXL3 4-bit weight-only experts, with 4-bit dense layers and FP8 KV. No…

        Read full on X, posted by @krunkosaurus

        @krunkosaurus · x.com

    2. Oct 101 post

      • https://t.co/AAMaMEGToz

        Read full on X, posted by @MiaAI_lab

        @MiaAI_lab · x.com

    3. 8 days earlier
    4. Oct 21 post

      • Just ran a race between both of @MiaAI_lab GLM recipes and it’s awesome to see the difference 🔥

        Read full on X, posted by @hecisaza

        @hecisaza · x.com

    5. Oct 12 posts3 posts

      • Pelican riding a bicycle. Local AI Generated.

        Read full on X, posted by @jaebird

        @jaebird · x.com

      • If anyone was wondering... C1-C12 - GLM 5.3 Flash - 2x DGX Sparks - TensorFold The biggest gap between TensorFold and vLLM is concurrency. I think with some more optimizations, TensorFolds speed…

        Read full on X, posted by @landontgreen

        @landontgreen · x.com

      • New recipe serves GLM-5.3 Flash on two desk-side DGX Sparks from one Weights are an unmodified EXL3 quant, not the abliterated one; the author's own spot-check reads GSM8K 98.0% on the 4-bit+FP8…

        Read full on X, posted by @jimmy_longbow_

        @jimmy_longbow_ · x.com

    You might also like

    Repositories close to MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold
    FeaturedAdvertise to 180K+ monthly visitors
    Bifrost

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

    Busbar

    Control what AI can do before it acts

    AxiomCode

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

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

    Python

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

    736145

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

    Shell

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

    27444

    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

    31431

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

    Python

    DeepSeek v4 Flash EXL3 on one DGX Spark

    34738

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

    HTML

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

    41157

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

    Python

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

    61091

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

    Python

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

    25142