#Unsloth
i think it’ll be a dynamic quant though :/ i’ve not been impressed by gsq rco and whatever unsloth calls theirs
November 16, 2026 at 4:01 AM
Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update | Discussion
Qwen3.8 - How to Run Locally | Unsloth Documentation
Guide to running Qwen3.8 quants including Qwen3.8-27B on your local setup.
unsloth.ai
November 14, 2026 at 4:00 AM
Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update
View Article | Discussion + AI Summary

Summary of HN discussion 🧵👇
Qwen3.8 - How to Run Locally | Unsloth Documentation
Guide to running Qwen3.8 quants including Qwen3.8-27B on your local setup.
unsloth.ai
November 15, 2026 at 7:00 PM
le dernier qwen unsloth est décevant ?
November 17, 2026 at 2:16 PM
Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update
https://unsloth.ai/docs/models/qwen3.8

https://news.ycombinator.com/item?id=50491980
Qwen3.8 - How to Run Locally | Unsloth Documentation
Guide to running Qwen3.8 quants including Qwen3.8-27B on your local setup.
unsloth.ai
November 14, 2026 at 7:45 AM
Desktop control starts disabled, with Unsloth asking permission before actions—and again before switching apps.

https://oossa.com/en/unsloth-beta-lets-ai-models-use-your-desktop-apps

#AI #GenerativeAI
Unsloth beta lets AI models use your desktop apps
Unsloth’s v0.1.918-beta adds screen, mouse and keyboard control, app connections for creative tools, and new MiniMax-H3-Image options.
oossa.com
November 16, 2026 at 3:13 PM
Unsloth 3.1にアップデートしただけで長考減るのなんでだ
November 16, 2026 at 1:03 PM
Fine-tuning Llama 3 8B with Unsloth + QLoRA teaches it to output schema-perfect JSON for tool calling—prompting alone can drift. Runs on free Colab T4 in under 10 minutes. 🤖🧠⚙️ #LLM #ToolCalling #QLoRA #Unsloth #FineTuning
How to Fine-Tune Llama 3 for Custom Tool Calling with Unsloth in Python - MachineLearningMastery.com
In this article, you will learn how to fine-tune Llama 3 8B for custom tool calling using Unsloth and QLoRA, so that the model reliably outputs structured JSON payloads for a specific API schema.
machinelearningmastery.com
November 16, 2026 at 6:39 AM
Today, we're releasing the highest accuracy Qwen3.8-27B GGUFs.

Our new Dynamic V3.1 GGUFs lead by 5–10% on average across Terminal Bench, DeepSWE & more. We’re working on an even better version for Qwen4.

Run on 12GB RAM setups

GGUF: huggingface.co/unsloth/Qwen...
Blog: unsloth.ai/docs/models/...
November 11, 2026 at 3:34 PM
Unsloth makes LLM fine-tuning feel routine with beginner-friendly notebooks, pip install, and big VRAM cuts. Once more people can train, dataset quality and evaluation decide whether speed turns into progress. Cheap tuning raises the value of evaluation. #AILiteracy
GitHub - unslothai/unsloth: Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more. - unslothai/unsloth
github.com
November 18, 2026 at 10:04 PM
Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update https://unsloth.ai/docs/models/qwen3.8 (http://news.ycombinator.com/item?id=50491980)
November 15, 2026 at 10:13 AM
Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update
Comments
unsloth.ai
November 14, 2026 at 10:19 AM
써본 로컬모델들 중에서는 아직까진 Qwen 3.8 베이스가 제일 괜찮은 것 같아요. 현 시점에는 Unsloth Q4로 3.8 27B Dense 돌리는게 전반적으로는 제일 가성비가 좋다고 봅니다.

만약 GPU랑 RAM, SSD 성능이 괜찮다면 Strata(Qwen 3.8 Next)를 쓰는게 좋다고 봐요. 제가 RAM이 모자라서 Strata를 풀성능으로 못쓰는게 아쉬울 따름.. 일반 컨슈머 레벨에선 이게 최선이지 않을까 싶습니다.
November 15, 2026 at 2:52 PM
1/ Unsloth released Dynamic v3.1 quantizations for Qwen3.8-27B with 5 to 10 percent accuracy improvements.
November 15, 2026 at 12:06 AM
Cómo correr Bonsai 27B en una GPU de 8 GB con LM Studio o Unsloth

Esta guía práctica muestra cómo correr Bonsai 27B en una GPU de 8 GB con Windows 11, con dos rutas completas y originales: una en LM Studio y otra en Unsloth Desktop, de modo que cada función que hoy pagan en ChatGPT Plus tenga un…
Cómo correr Bonsai 27B en una GPU de 8 GB con LM Studio o Unsloth
Esta guía práctica muestra cómo correr Bonsai 27B en una GPU de 8 GB con Windows 11, con dos rutas completas y originales: una en LM Studio y otra en Unsloth Desktop, de modo que cada función que hoy pagan en ChatGPT Plus tenga un equivalente local y gratuito. La tabla de equivalencias facilita decidir antes de instalar nada.
onedigital.mx
November 18, 2026 at 12:16 AM
Cómo correr Bonsai 27B en una GPU de 8 GB con LM Studio o Unsloth

Esta guía práctica muestra cómo correr Bonsai 27B en una GPU de 8 GB con Windows 11, con dos rutas completas y originales: una en LM Studio y otra en Unsloth Desktop, de modo que cada función que hoy pagan en ChatGPT Plus tenga un…
Cómo correr Bonsai 27B en una GPU de 8 GB con LM Studio o Unsloth
Esta guía práctica muestra cómo correr Bonsai 27B en una GPU de 8 GB con Windows 11, con dos rutas completas y originales: una en LM Studio y otra en Unsloth Desktop, de modo que cada función que hoy pagan en ChatGPT Plus tenga un equivalente local y gratuito. La tabla de equivalencias facilita decidir antes de instalar nada.
onedigital.mx
November 18, 2026 at 12:16 AM
[some-subscribed-rss] New Post: Unsloth Lets You Run and Fine-Tune AI Models on Your Own Hardware, by Jeremy https://noted.lol/unsloth/
November 17, 2026 at 12:55 PM
Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update (@unsloth.ai)

Discussion | Main Link
November 14, 2026 at 8:11 AM
Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update
https://unsloth.ai/docs/models/qwen3.8
https://news.ycombinator.com/item?id=50491980
November 15, 2026 at 4:38 AM
Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update https://unsloth.ai/docs/models/qwen3.8 (https://news.ycombinator.com/item?id=50491980)
Qwen3.8 - How to Run Locally | Unsloth Documentation
Guide to running Qwen3.8 quants including Qwen3.8-27B on your local setup.
unsloth.ai
November 14, 2026 at 5:19 AM
Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update https://unsloth.ai/docs/models/qwen3.8 (https://news.ycombinator.com/item?id=50491980)
Qwen3.8 - How to Run Locally | Unsloth Documentation
Guide to running Qwen3.8 quants including Qwen3.8-27B on your local setup.
unsloth.ai
November 14, 2026 at 3:29 AM
Unsloth Qwen3.8-27B Quantizations – Dynamic v3.1 Update https://unsloth.ai/docs/models/qwen3.8 (http://news.ycombinator.com/item?id=50491980)
November 14, 2026 at 2:33 PM