🔄 In a Training Loop

Cory Malterer

joeblowma

13 46

joeblowma

AI & ML interests

Where exactly is the seed that grew the tree?

Recent Activity

liked a model 4 days ago

Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B

liked a model 7 days ago

deepgrove/maple-preview

liked a model 8 days ago

Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B

View all activity

Organizations

None yet

liked a model 4 days ago

Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B

Text Generation • 10B • Updated 4 days ago • 208 • 9

liked a model 7 days ago

deepgrove/maple-preview

Text Generation • 20B • Updated 7 days ago • 2.05k • 330

liked a model 8 days ago

Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B

Text Generation • 5B • Updated 5 days ago • 4.1k • 9

liked a model 11 days ago

mradermacher/Kimi-VL-A3B-Thinking-2506-i1-GGUF

16B • Updated Dec 14, 2025 • 1.27k • 15

liked a model 18 days ago

DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

Image-Text-to-Text • 9B • Updated 5 days ago • 419k • 340

liked a model 20 days ago

prism-ml/Bonsai-27B-gguf

Text Generation • 27B • Updated 25 days ago • 2.71M • 761

liked 3 models 23 days ago

liked a model 30 days ago

deepseek-ai/DeepSeek-R1

Text Generation • 685B • Updated Mar 27, 2025 • 8.52M • • 13.6k

liked 3 models about 1 month ago

Qwen/Qwen3.5-9B-Base

Image-Text-to-Text • 10B • Updated Apr 23 • 331k • 98

Qwen/Qwen3.5-4B-Base

Image-Text-to-Text • 5B • Updated Apr 23 • 220k • 80

fableforge-ai/NEXUS-Coder

Text Generation • 2B • Updated 26 days ago • 587 • 5

reacted to danielhanchen's post with 🚀 about 1 month ago

Post

4365

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