Thor Lin

coolthor

·

http://www.ai-muninn.com

coolthor

AI & ML interests

On-device & edge LLM inference on NVIDIA GB10 / DGX Spark. Quantization (NVFP4 W4A4/W4A16, FP8), vLLM serving, speculative decoding (EAGLE-3), and multimodal/omni models. Measure-first benchmarking — I publish the numbers, including the ones that fail.

Recent Activity

liked a model about 11 hours ago

moonshotai/Kimi-K3

updated a model 7 days ago

coolthor/Sulphur-2-distilled-Q4_K_M-GGUF

updated a model 7 days ago

coolthor/Laguna-S-2.1-attnQ8-DFlash-Q4-GGUF

View all activity

Organizations

None yet

liked a model about 11 hours ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 1 day ago • 99.2k • • 8.15k

liked a model 17 days ago

empero-ai/Qwythos-9B-v2-GGUF

Image-Text-to-Text • 9B • Updated 17 days ago • 413k • 227

liked 2 models 3 months ago

coolthor/Gemma-4-E4B-it-NVFP4A16

Image-Text-to-Text • 7B • Updated Jun 2 • 1.1k • 1

coolthor/Huihui-Qwen3.6-35B-A3B-abliterated-FP8-DYNAMIC

Image-Text-to-Text • 36B • Updated 28 days ago • 400k • 3

liked a model 5 months ago

Qwen/Qwen3.5-35B-A3B

Image-Text-to-Text • 36B • Updated Apr 24 • 2.57M • • 1.48k