Unsloth Backup Account

company

http://www.unsloth.ai

unslothai

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

danielhanchen updated a model 3 days ago

unslothai/Qwen3-ASR-1.7B-GGUF

danielhanchen updated a model 3 days ago

unslothai/Qwen3-ASR-0.6B-GGUF

danielhanchen published a model 3 days ago

unslothai/Qwen3-ASR-0.6B-GGUF

View all activity

danielhanchen

posted an update 1 day ago

Post

311

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

danielhanchen

updated 2 models 3 days ago

unslothai/Qwen3-ASR-1.7B-GGUF

2B • Updated 3 days ago • 264

unslothai/Qwen3-ASR-0.6B-GGUF

0.8B • Updated 3 days ago • 257

danielhanchen

published 2 models 3 days ago

unslothai/Qwen3-ASR-0.6B-GGUF

0.8B • Updated 3 days ago • 257

unslothai/Qwen3-ASR-1.7B-GGUF

2B • Updated 3 days ago • 264

danielhanchen

posted an update 8 days ago

Post

1332

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

1 reply

danielhanchen

posted an update 9 days ago

Post

3958

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

5 replies

danielhanchen

posted an update 18 days ago

Post

4891

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

3 replies

danielhanchen

posted an update 20 days ago

Post

5926

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