gg-hf-st

gg-hf-st's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

danielhanchen 

posted an update 4 days ago

view post

Post

692

DeepSeek-V4-Flash can now run 2× faster locally with DSpark! ⚡️

DSpark enables V4-Flash-0731 GGUFs to generate ~1.4–2× faster with no accuracy change.

DeepSeek-V4-Flash-0731 can reach at 120 tokens/s.

GGUFs: unsloth/DeepSeek-V4-Flash-0731-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4

See translation

• 
• 

🔥

2

2

🤗

1

1

+

Reply

danielhanchen 

posted an update 11 days ago

view post

Post

1472

We compared 1-bit Kimi K3 to Claude Opus 5 and GPT 5.6. 🤯

We gave 4 models the same prompt: Create a glass aquarium whose side panel develops a visible crack and then bursts...

1-bit Kimi K3 GGUF ran locally on 4x B200s at 36 tok/s.

GGUF: unsloth/Kimi-K3-GGUF
GitHub repo: https://github.com/unslothai/unsloth

See translation

• 

• 
• 1 reply

·

👍

2

2

🔥

1

1

🤗

1

1

+

Reply

danielhanchen 

posted an update 12 days ago

view post

Post

4071

Kimi K3 can now be run locally! ✨

The 1-bit model retains ~78.9% accuracy after we shrunk it from 1.56TB to 594GB (-62% size).

Run on a Mac Studio connected with 128GB RAM device. Kimi K3 is the strongest open model to date.

GGUF: unsloth/Kimi-K3-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k3

See translation

• 
• 

• 
• 
• 
• 5 replies

·

❤️

11

11

🔥

9

9

👍

3

3

🤗

1

1

+

Reply

MaartenGr 

authored a paper 21 days ago

Gemma 4 Technical Report

Paper • 2607.02770 • Published Jul 2 • 76

danielhanchen 

posted an update 21 days ago

view post

Post

4947

Introducing Unsloth for AMD 🚀
You can now train & run LLMs on your AMD hardware

• We collaborated with AMD to enable you to train & run 500+ models on AMD GPUs
• Works on Windows, WSL, Linux
• Train Qwen, Gemma on just 3GB VRAM

GitHub: https://github.com/unslothai/unsloth
Blog + Guide: https://unsloth.ai/docs/basics/amd

See translation

• 
• 

• 
• 
• 
• 3 replies

·

🔥

27

27

❤️

10

10

🚀

6

6

🤗

6

6

👀

5

5

👍

5

5

🧠

3

3

➕

3

3

🤯

3

3

🤝

2

2

😎

2

2

+

Reply

danielhanchen 

posted an update 23 days ago

view post

Post

5986

Gemma 4 is now faster and much more accurate! 🚀

Google made huge improvements to tool-calling and chat accuracy, reliability + speed.
To get fixes, re-download our updated GGUF, MLX, NVFP4 quants!

Unsloth quants: https://huggingface.co/collections/unsloth/gemma-4
Gemma 4 Guide: https://unsloth.ai/docs/models/gemma-4

See translation

• 
• 
• 

• 
• 
• 
• 8 replies

·

🚀

30

30

👍

15

15

😎

6

6

🤗

5

5

🤝

1

1

+

Reply

danielhanchen 

posted an update 27 days ago

view post

Post

4808

We’re releasing Gemma 4 NVFP4 quants that run 1.5× faster on your GPU.

Gemma-4-12B NVFP4 works on 11GB VRAM.
26B-A4B hits 13K tok/s (B200).

Unsloth NVFP4 enables faster, more accurate 4-bit Blackwell inference.

Blog: https://unsloth.ai/docs/basics/nvfp4
Gemma NVFP4: https://huggingface.co/collections/unsloth/nvfp4

See translation

• 
• 

• 
• 
• 
• 3 replies

·

🔥

12

12

🤗

3

3

🚀

2

2

👍

2

2

+

Reply

danielhanchen 

posted an update about 1 month ago

view post

Post

4357

We’re releasing new Qwen3.6 quants that run 2.5× faster on your GPU. ⚡

Qwen3.6-27B NVFP4 runs on 24GB VRAM.
35B-A3B can hit 17,561 tok/s (B200).

We also improved accuracy, tool calling, agent use, and looping.

Qwen3.6 NVFP4: https://huggingface.co/collections/unsloth/nvfp4
Guide: https://unsloth.ai/docs/models/qwen3.6#nvfp4

See translation

• 
• 

• 
• 1 reply

·

🚀

15

15

🔥

11

11

🤗

1

1

+

Reply

osanseviero 

authored a paper about 1 month ago

Gemma 4 Technical Report

Paper • 2607.02770 • Published Jul 2 • 76

osanseviero 

submitted a paper to Daily Papers about 1 month ago

Gemma 4 Technical Report

Paper • 2607.02770 • Published Jul 2 • 76

danielhanchen 

posted an update about 1 month ago

view post

Post

6320

DeepSeek-V4 can now run locally with Unsloth GGUFs! 🐳

Run lossless DeepSeek-V4-Flash on 168GB RAM or
3-bit works on 110GB Mac, RAM, VRAM setups.

Run via Unsloth Studio or llama.cpp.

GGUF: unsloth/DeepSeek-V4-Flash-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4

See translation

• 
• 
• 

🔥

20

20

🚀

5

5

👍

3

3

🤗

2

2

+

Reply

danielhanchen 

posted an update about 2 months ago

view post

Post

3389

1-bit GLM-5.2 GGUF vs. Claude 4.8 Opus vs. GPT-5.5

We gave 3 models the same prompt and compared one-shot outputs.

The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s.

Which output do you like best?
GGUF: unsloth/GLM-5.2-GGUF

See translation

• 
• 

• 
• 
• 3 replies

·

🤗

11

11

👍

4

4

🔥

1

1

+

Reply

danielhanchen 

posted an update about 2 months ago

view post

Post

4626

Google's new DiffusionGemma can now run at 2000+ tokens/sec! ⚡

We made local DiffusionGemma inference 1.8× faster.
Run it on 18GB RAM via Unsloth Studio.

GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/models/diffusiongemma

See translation

• 
• 

• 
• 
• 
• 4 replies

·

🔥

8

8

🤗

2

2

😔

1

1

+

Reply

danielhanchen 

posted an update 2 months ago

view post

Post

1206

Google releases DiffusionGemma.✨
The new 26B-A4B diffusion text model runs locally on 18GB RAM.

Run with 4x faster text generation, thinking, image, video and 256K context. Run and train via Unsloth Studio.

GGUF: unsloth/diffusiongemma-26B-A4B-it-GGUF
Guide: https://unsloth.ai/docs/models/diffusiongemma

See translation

• 
• 

• 
• 1 reply

·

🔥

3

3

🤗

1

1

+

Reply

osanseviero 

updated a model 2 months ago

google/diffusiongemma-26B-A4B-it

Image-Text-to-Text • 26B • Updated 26 days ago • 1.88M • 1.17k

MaartenGr 

updated a model 2 months ago

google/diffusiongemma-26B-A4B-it

Image-Text-to-Text • 26B • Updated 26 days ago • 1.88M • 1.17k

danielhanchen 

posted an update 2 months ago

view post

Post

4312

Google releases Gemma 4 QAT. ✨
You can now run Gemma 4 at 3x less memory with near original performance.

QAT makes it possible to run Gemma 4 26B-A4B on 16GB RAM.

GGUFs: https://huggingface.co/collections/unsloth/gemma-4-qat
QAT Guide: https://unsloth.ai/docs/models/gemma-4/qat

See translation

• 
• 

• 
• 1 reply

·

👍

17

17

🚀

4

4

🤗

1

1

😎

1

1

+

Reply

danielhanchen 

posted an update 2 months ago

view post

Post

9373

Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs.

Google's new model, Gemma 4 12B Unified supports image, audio and 256K context.
You can run and train the model via Unsloth Studio.

GGUF: unsloth/gemma-4-12b-it-GGUF
Guide: https://unsloth.ai/docs/models/gemma-4

See translation

• 
• 

• 
• 
• 
• 5 replies

·

🔥

44

44

👍

13

13

🤗

2

2

+

Reply

danielhanchen 

posted an update 3 months ago

view post

Post

2849

Qwen3.6 MTP is here! Run locally on 20GB RAM. ⚡️

MTP enables Qwen3.6 to generate ~1.4–2.2× faster with no accuracy change.

Qwen3.6-27B: unsloth/Qwen3.6-27B-MTP-GGUF
Qwen3.6-35B-A3B: unsloth/Qwen3.6-35B-A3B-MTP-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.6#mtp-guide

See translation

• 
• 

• 
• 
• 2 replies

·

👍

12

12

🔥

4

4

🤗

3

3

🚀

3

3

❤️

1

1

🧠

1

1

😎

1

1

+

Reply

danielhanchen 

posted an update 3 months ago

view post

Post

6009

We’re excited to announce that Unsloth has joined the PyTorch Ecosystem! 🔥🦥

Unsloth is an open-source project that makes training & running models more accurate and faster with less compute. Our mission is to make local AI accessible to everyone. Thanks to all of you for making this possible! 💕

Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth

See translation

• 

• 
• 
• 2 replies

·

❤️

42

42

🚀

16

16

🔥

14

14

🤗

5

5

+

Reply