architectds/collabosm

Run Qwen3.8-Flash-Next (125B-A6B MoE) on ONE Colab A100-80GB High-RAM: pinned runtime, weights from HF, OpenAI-compatible endpoint, measured 2.8k-3.9k t/s prefill / 90-97 t/s decode, plus a verified pinned-RAM KV tier.

Language modelsPython

3.8 Early signal Magnitude out of 10 — how fast interest is growing, not a quality score. Star growth looks organic. Data as of September 26, 2026, 02:37 UTC.

Open on Seismograph Open on GitHub

About the project

A set of scripts to run Qwen3.8-Flash-Next (125B MoE) on a single Colab A100-80GB High-RAM with an OpenAI-compatible endpoint and measured throughput.

Useful for

Deploy an OpenAI-compatible Qwen3.8-Flash-Next endpoint on a Colab A100 for client testing
Measure model prefill and decode throughput at different GCS and NDT settings
Stop the VM via down.sh to avoid burning Colab compute units

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

0 stars so far today, about 33 expected by the end of the day.
The spike has held for 2 days in a row — not a one-off blip.
The repository is 1 day old and already has 72 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
Top new repositories this week: #186.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 72
Today: 0 · ≈ 32 by evening
Forks: 2
Issues and pull requests: 0
Watchers: 0
Language: Python
License: MIT
Created: September 25, 2026
Last push: September 26, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 26, 2026Top new repositories this week: #184

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/architectds/collabosm.svg?lang=en)](https://gitnova.dev/en/r/architectds/collabosm)

More in this category

6.9
ollaya-dev/ollaya
A local runtime for decision models: pulls and serves classification and routing models behind a TypeSafe-compatible API. Like Ollama, but for models that return probabilities instead of text.

Early signalLanguage modelsRust+0 stars today, ≈ 134 by evening
6.4
NVIDIA/Model-Optimizer
NVIDIA library for compressing and accelerating models: quantization, pruning, distillation, NAS and speculative decoding with export to TensorRT-LLM, vLLM, SGLang. For ML engineers preparing models for deployment.

BreakoutLanguage modelsPython+0 stars today, ≈ 255 by evening
5.4
nokia-applied-research/AnyJev
Turns any LLM into a decision model with typed questions (choice, yes/no, score) that return real probabilities read from the next-token distribution, without training. L0 removes position and label-prior bias; L1 adds…

Early signalLanguage modelsPython+0 stars today, ≈ 152 by evening
4.7
Badtheorylabs/interference-search
A search method that reasons over explicit states instead of a language model's linear transcript: many branches expand at once, duplicates merge, dead ends are dropped by a trained judge, and survivors advance…

Early signalLanguage modelsPython+0 stars today, ≈ 81 by evening
4.4
Liuziyu77/Valen
A multimodal decision model built on a Qwen3.5-0.8B/2B backbone: it takes text, images and video with an instruction and returns probabilities over supplied candidates without generating answer tokens. The repo…

Early signalLanguage modelsPython+0 stars today, ≈ 59 by evening
4.3
mizorewww/laya-mlx
Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.

CoolingLanguage modelsPython+0 stars today, ≈ 71 by evening