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

VeroFess/llama.cpp_3090x2_qwen3.8_q8_opt

A llama.cpp fork with TurboQuant/TCQ KV cache, fused Qwen MTP speculative decoding, and multi-GPU long-context serving fixes.

#LLM inference
Visit GitHub
C++
24
4
1,887 contributors
MIT License
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

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

Momentum

How fast VeroFess/llama.cpp_3090x2_qwen3.8_q8_opt 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 27 – Oct 26, 2026

Stars +5 in 61 days

01
1

Forks +1 in 61 days

01
1

Merged PRs 0 in 61 days

01

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

Not in the Trendshift top 25 in this period

Aug 27Sep 4Sep 12Sep 20Sep 28Oct 6Oct 14Oct 22
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, Aug 27, 2026+1+00
Fri, Aug 28, 2026+0+00
Sat, Aug 29, 2026+0+00
Sun, Aug 30, 2026+0+00
Mon, Aug 31, 2026+0+00
Tue, Sep 1, 2026+0+00
Wed, Sep 2, 2026+1+10
Thu, Sep 3, 2026+0+00
Fri, Sep 4, 2026+0+00
Sat, Sep 5, 2026+0+00
Sun, Sep 6, 2026+0+00
Mon, Sep 7, 2026+0+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+1+00
Sun, Sep 13, 2026+0+00
Mon, Sep 14, 2026+0+00
Tue, Sep 15, 2026+0+00
Wed, Sep 16, 2026+1+00
Thu, Sep 17, 2026+0+00
Fri, Sep 18, 2026+0+00
Sat, Sep 19, 2026+0+00
Sun, Sep 20, 2026+1+00
Mon, Sep 21, 2026+0+00
Tue, Sep 22, 2026+0+00
Wed, Sep 23, 2026+0+00
Thu, Sep 24, 2026+0+00
Fri, Sep 25, 2026+0+00
Sat, Sep 26, 2026+0+00
Sun, Sep 27, 2026+0+00
Mon, Sep 28, 2026+0+00
Tue, Sep 29, 2026+0+00
Wed, Sep 30, 2026+0+00
Thu, Oct 1, 2026+0+00
Fri, Oct 2, 2026+0+00
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+0+00
Mon, Oct 5, 2026+0+00
Tue, Oct 6, 2026+0+00
Wed, Oct 7, 2026+0+00
Thu, Oct 8, 2026+0+00
Fri, Oct 9, 2026+0+00
Sat, Oct 10, 2026+0+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+0+00
Tue, Oct 13, 2026+0+00
Wed, Oct 14, 2026+0+00
Thu, Oct 15, 2026+0+00
Fri, Oct 16, 2026+0+00
Sat, Oct 17, 2026+0+00
Sun, Oct 18, 2026+0+00
Mon, Oct 19, 2026+0+00
Tue, Oct 20, 2026+0+00
Wed, Oct 21, 2026+0+00
Thu, Oct 22, 2026+0+00
Fri, Oct 23, 2026+0+00
Sat, Oct 24, 2026+0+00
Sun, Oct 25, 2026+0+00
Mon, Oct 26, 2026+0+00
Total+5+10
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Aug 181 post

    • 搞定了双 3090 跑 qwen 3.8 27b q8 1 并发最高 80t/s 8 并发平均 124t/s 应该是现在跑q8最便宜的可用速度方案…… 而且输出完全可用啊！

      Read full on X, posted by @VeroFess

      @VeroFess · x.com

You might also like

Repositories close to VeroFess/llama.cpp_3090x2_qwen3.8_q8_opt
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

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

sergiuszm/ninfer-4090

C++

Qwen3.8-27B on one RTX 4090: full native 262K context via E8 4-bit KV, up to 149 tok/s code decode with MTP3, sm_89-retuned attention prefill, vision, llama.cpp-compatible /metrics + /slots

21742

r0b0tlab/qwen38-exl3-dflash2

Python

Qwen3.8-27B EXL3 (4.00 bpw) + DFlash2 speculative decoding for ExLlamaV3, validated at 262k context on a 24 GB RTX 3090

253

Don-Chad/ninfer-3090

C++

Hyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux builds.

47555

MiaAI-Lab/Qwen3.8-27B-DFlash2-EXL3-5.0bpw

Python

Deployment kit: Qwen3.8-27B EXL3 3.5bpw target + DFlash2 EXL3 5.0bpw speculative draft — launcher, config, model cards

23225

skrodahl/qwen38-27B-dual-rtx5060

Python
347

DominikBucko/qwen38-flash-next-2x3090

Python

Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,865 tok/s; with 64 GB RAM 3,410 tok/s prefill · 84 tok/s decode. New: opt-in uncensored mode (runtime abliteration, no new weights).

12717

UDPSendToFailed/ninfer-4090

C++

NInfer port for Qwen 3.8 27B on RTX 4090

18127

frankkk96/FlashQwen

Go

From-scratch C++/CUDA inference engine for Qwen3-8B

853

roofkid/ninfer-4080

C++

Qwen3.8-27B-GSQ3 on one RTX 4080: 100k context with rk4v4-e8, up to 2720 tok/s prefill and 262 tok/s generation

303