OSS Radar
MakazhanAlpamys/Soup
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. Why it matters: useful plumbing for shipping LLM-powered features.
GitHub description: Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Stars
8.7k
Last 24h
+37est.
Last 7 days
+259est.
Forks
1.4k
Star history (last 1 snapshot)
Only one snapshot so far. The chart fills in as OSS Radar collects daily snapshots.
* / est. Estimated: until we have enough daily snapshots for a repo, its gain is total stars ÷ days since creation. Measured numbers replace estimates automatically.
Maintainer? Add the badge to your README
Shows your live OSS Radar rank and links back here. Updates hourly.
[](https://ossradar.net/repo/MakazhanAlpamys/Soup)<a href="https://ossradar.net/repo/MakazhanAlpamys/Soup"><img src="https://ossradar.net/badge/MakazhanAlpamys/Soup" alt="Trending on OSS Radar"></a>About Soup
MakazhanAlpamys/Soup is a Python project in the LLM tooling category, created 8 months ago. It has 8.7k GitHub stars and 1.4k forks, and gained +259 stars over the last 7 days (early estimate), ranking #137 of 167 LLM tooling repos tracked by OSS Radar this week.
See more trending LLM tooling repos or the top AI repos this week.
- Language
- Python
- Category
- LLM tooling
- Created
- Feb 20, 2026
- Last push
- Oct 13, 2026
- cli
- consumer-gpu
- dpo
- fine-tuning
- gguf
- huggingface
- llm
- llmops
- local-ai
- local-llm
- lora
- low-vram
- machine-learning
- ollama
- peft
- python
- pytorch
- qlora
- sft
- transformers
Similar rising repos
- hiyouga/LlamaFactory+428est.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024). Why it matters: useful plumbing for shipping LLM-powered features.
- rohitg00/ai-engineering-from-scratch+2.3kest.
Learn AI Engineering! Learn it. Build it. Ship it for others. Why it matters: useful plumbing for shipping LLM-powered features.
- huggingface/transformers+404est.
Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both… Why it matters: useful plumbing for shipping LLM-powered features.
- unslothai/unsloth+520est.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more. Why it matters: useful plumbing for shipping LLM-powered features.
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it. Why it matters: useful plumbing for shipping LLM-powered features.
- lyogavin/airllm+218est.
AirLLM 2.8T LLM inference with single 4GB GPU. Why it matters: useful plumbing for shipping LLM-powered features.