-
unsloth/Qwen3-30B-A3B-GGUF
Text Generation • 31B • Updated • 77.7k • 265 -
lmstudio-community/Qwen3-4B-GGUF
Text Generation • 4B • Updated • 6.18k • 14 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 19k • 370 -
unsloth/gemma-3-27b-it-GGUF
Any-to-Any • 27B • Updated • 58.9k • 178
Shreyan C
thethinkmachine
AI & ML interests
🦜AI Engineer
Recent Activity
updated
a dataset
6 days ago
thethinkmachine/trackio-dataset
updated
a dataset
10 days ago
thethinkmachine/trackio-dataset
updated
a dataset
10 days ago
thethinkmachine/trackio-dataset
Organizations
-
Qwen/Qwen3-4B
Text Generation • 4B • Updated • 3.94M • • 504 -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 855k • 1.07k -
Qwen/Qwen3-8B
Text Generation • 8B • Updated • 4.33M • • 827 -
ByteDance-Seed/Seed-Coder-8B-Reasoning
Text Generation • 8B • Updated • 555 • 149
Some really good 32B dense models to watch out for!
-
Qwen/Qwen3-32B
Text Generation • 33B • Updated • 3.19M • • 606 -
Qwen/QwQ-32B
Text Generation • 33B • Updated • 97.8k • • 2.87k -
Qwen/Qwen2.5-Coder-32B-Instruct
Text Generation • 33B • Updated • 143k • • 1.96k -
Qwen/Qwen2.5-VL-32B-Instruct
Image-Text-to-Text • 33B • Updated • 232k • • 473
Some really good MoEs to watch out for!
-
unsloth/Qwen3-30B-A3B-GGUF
Text Generation • 31B • Updated • 77.7k • 265 -
lmstudio-community/Qwen3-4B-GGUF
Text Generation • 4B • Updated • 6.18k • 14 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 19k • 370 -
unsloth/gemma-3-27b-it-GGUF
Any-to-Any • 27B • Updated • 58.9k • 178
Some really good 32B dense models to watch out for!
-
Qwen/Qwen3-32B
Text Generation • 33B • Updated • 3.19M • • 606 -
Qwen/QwQ-32B
Text Generation • 33B • Updated • 97.8k • • 2.87k -
Qwen/Qwen2.5-Coder-32B-Instruct
Text Generation • 33B • Updated • 143k • • 1.96k -
Qwen/Qwen2.5-VL-32B-Instruct
Image-Text-to-Text • 33B • Updated • 232k • • 473
-
Qwen/Qwen3-4B
Text Generation • 4B • Updated • 3.94M • • 504 -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 855k • 1.07k -
Qwen/Qwen3-8B
Text Generation • 8B • Updated • 4.33M • • 827 -
ByteDance-Seed/Seed-Coder-8B-Reasoning
Text Generation • 8B • Updated • 555 • 149
Some really good MoEs to watch out for!