Hugging Face Party @ PyTorch Conference

community

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

JingzeShi authored a paper 26 days ago

Towards Automated Kernel Generation in the Era of LLMs

JingzeShi authored a paper 26 days ago

OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale

JingzeShi submitted a paper 26 days ago

OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale

View all activity

danielhanchen

posted an update 1 day ago

Post

1334

You can now fine-tune Qwen3.5 for free with our notebook! 🔥

You just need 5GB VRAM to train Qwen3.5-2B LoRA locally!

Unsloth trains Qwen3.5 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/models/qwen3.5/fine-tune
Qwen3.5-4B Colab: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_5_(4B)_Vision.ipynb

danielhanchen

posted an update 4 days ago

Post

5072

Qwen releases 4 new Qwen3.5 Small models: 0.8B • 2B • 4B • 9B!

Run Qwen3.5-0.8B, 2B and 4B on your phone. Run 9B on 6GB RAM.

The vision reasoning LLMs perform better than models 4x their size.

GGUFs to run: https://huggingface.co/collections/unsloth/qwen35

Guide: https://unsloth.ai/docs/models/qwen3.5

4 replies

danielhanchen

posted an update 11 days ago

Post

3396

100,000+ models trained with Unsloth have now been open-sourced on 🤗Hugging Face! 🦥

Here are the most popular ones you can run local:
1. TeichAI - GLM-4.7-Flash distilled from Claude 4.5 Opus (high)
2. Zed - Qwen Coder 7B fine-tuned for stronger coding
3. DavidAU - Llama-3.3-8B distilled from Claude 4.5 Opus (high)
4. huihui - gpt-oss made “abliberated”

Links to models:
1. TeichAI: TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF
2. Zed: zed-industries/zeta
3. DavidAU: DavidAU/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning
4. huihui: huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated

See all the 100K latest models fine-tuned with Unsloth here: https://huggingface.co/models?other=u

2 replies

danielhanchen

posted an update 15 days ago

Post

2661

We collabed with HF on showing how you can use HF Jobs and Unsloth! https://huggingface.co/blog/unsloth-jobs

danielhanchen

posted an update 18 days ago

Post

5651

You can now run Qwen3.5 locally! 💜
Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. It performs on par with Gemini 3 Pro, Claude Opus 4.5 & GPT-5.2.

GGUF: unsloth/Qwen3.5-397B-A17B-GGUF
Run Dynamic 3-bit on a 192GB Mac for 20 tokens/s.

Guide: https://unsloth.ai/docs/models/qwen3.5

9 replies

danielhanchen

posted an update 19 days ago

Post

8459

You can now run MiniMax-2.5 locally! 🚀
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.

Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF

1 reply

1aurent

authored a paper 24 days ago

Ministral 3

Paper • 2601.08584 • Published Jan 13 • 55

danielhanchen

posted an update 24 days ago

Post

5173

We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗

Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe

1 reply

JingzeShi

authored 2 papers 26 days ago

Towards Automated Kernel Generation in the Era of LLMs

Paper • 2601.15727 • Published Jan 22 • 19

OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale

Paper • 2602.05711 • Published 29 days ago • 10

JingzeShi

submitted a paper to Daily Papers 26 days ago

OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale

Paper • 2602.05711 • Published 29 days ago • 10

danielhanchen

posted an update 29 days ago

Post

3698

We created a tool-calling guide for local LLMs!

Learn how to use any open model like Qwen3-Coder-Next and GLM-4.7-Flash for function calling.

Guide: https://unsloth.ai/docs/basics/tool-calling-guide-for-local-llms

We provide hands-on examples for: story writing, Python execution, terminal tool calls, maths and more.

7 replies

danielhanchen

posted an update about 1 month ago

Post

3762

Qwen releases Qwen3-Coder-Next! 💜 Run the locally on 46GB RAM or less.

Thhe model excels at agentic coding & local use. With 256K context, it delivers similar performance to models with 10-20× more active parameters.

GGUF: unsloth/Qwen3-Coder-Next-GGUF
Guide: https://unsloth.ai/docs/models/qwen3-coder-next

10 replies

danielhanchen

posted an update about 1 month ago

Post

3449

You can now run Kimi K2.5 locally! 🔥

We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.

GGUF: unsloth/Kimi-K2.5-GGUF

Guide: https://unsloth.ai/docs/models/kimi-k2.5

7 replies

danielhanchen

posted an update about 1 month ago

Post

2627

You can now fine-tune embedding models in our free Unsloth notebook! 🤗

Fine-tuning embedding models improves retrieval & RAG by aligning vectors to your domain-specific notion of similarity, improving search, clustering, and recommendations on your data.

⭐ Blog + Notebooks: https://unsloth.ai/docs/new/embedding-finetuning

Unsloth trains embedding models 1.8-3.3x faster with 20% less VRAM, 2x longer context & no accuracy loss vs. FA2 setups.

We'd like to thank Hugging Face and Unsloth contributor: electroglyph for making this possible!

3 replies

danielhanchen

posted an update about 2 months ago

Post

2632

Run GLM-4.7-Flash locally on your device with 24GB RAM!🔥

It's the best performing 30B model on SWE-Bench and GPQA. With 200K context, it excels at coding, agents, chat & reasoning.

GGUF: unsloth/GLM-4.7-Flash-GGUF

Guide: https://unsloth.ai/docs/models/glm-4.7-flash

danielhanchen

posted an update about 2 months ago

Post

2868

You can now do reinforcement learning training with 7× longer context and no accuracy loss, via our new batching algorithms.

Long reasoning chains in RL are costly, but now we enable you to train gpt-oss with GRPO & reach 380K context on a 192GB GPU.

Blog: https://unsloth.ai/docs/new/grpo-long-context

andreaskoepf

authored 3 papers about 2 months ago

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Paper • 1912.01703 • Published Dec 3, 2019 • 1

MEDITRON-70B: Scaling Medical Pretraining for Large Language Models

Paper • 2311.16079 • Published Nov 27, 2023 • 19

REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards

Paper • 2505.24760 • Published May 30, 2025 • 74

AI & ML interests

Recent Activity

Team members 196

HF-Party's activity