jmnargi/Strata-V100

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 29 – Oct 22, 2026

Stars +75 in 24 days

Forks +10 in 24 days

Merged PRs 68 in 24 days

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

Not in the Trendshift top 25 in this period

Sep 29Oct 2Oct 5Oct 8Oct 11Oct 14Oct 17Oct 20

Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day	Stars gained	Forks gained	Merged PRs
Tue, Sep 29, 2026	+0	+0	3
Wed, Sep 30, 2026	+0	+0	0
Thu, Oct 1, 2026	+0	+0	8
Fri, Oct 2, 2026	+1	+1	3
Sat, Oct 3, 2026	+7	+0	6
Sun, Oct 4, 2026	+9	+0	9
Mon, Oct 5, 2026	+7	+0	4
Tue, Oct 6, 2026	+3	+0	3
Wed, Oct 7, 2026	+6	+1	8
Thu, Oct 8, 2026	+1	+0	1
Fri, Oct 9, 2026	+4	+0	2
Sat, Oct 10, 2026	+4	+1	4
Sun, Oct 11, 2026	+2	+2	4
Mon, Oct 12, 2026	+4	+1	0
Tue, Oct 13, 2026	+3	+0	3
Wed, Oct 14, 2026	+4	+1	1
Thu, Oct 15, 2026	+2	+0	0
Fri, Oct 16, 2026	+5	+2	2
Sat, Oct 17, 2026	+1	+0	3
Sun, Oct 18, 2026	+5	+0	0
Mon, Oct 19, 2026	+3	+0	1
Tue, Oct 20, 2026	+3	+1	2
Wed, Oct 21, 2026	+1	+0	1
Thu, Oct 22, 2026	+0	+0	0
Total	+75	+10	68

#1 on the list
Rank that day
Not trending

Niko1221/Strata

C++

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

30k3.1k

mach10x/strata

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

14119

Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more. Setup installs our GPTQ quants (huihui abliterated, OrcaRouter) from Hugging Face. CPU experts on AVX-512 or AVX2 (+AVX-VNNI), all experts in RAM from 92 GB, a low-RAM mode below, vision, W4A8 prompts. Windows / CUDA 13.

18419

robertkarl/UnbiasedStrata

C++

Strata minus the bullshit. clone, rsync to prod, compile and go

14435

yibie/strata-mlx

Python

Qwen3.8-Flash-Next on Apple Silicon: an MLX engine that reads Strata's GGUF files and speaks its line protocol (unofficial)

10415

architectds/Strata

C++

Qwen3.8-Flash-Next (125B MoE) on a 8GB+ NVIDIA GPU: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

877

jesdga95/basalt

C++

Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell

12216

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

dnv2003/v100-skinny

Python

Hand-written NVFP4 W4A16 CUDA kernels for Volta

17527

Momentum