coolthor/MiniMax-H3-pruned-NVFP4
Image-Text-to-Video • Updated • 5
Thor Lin
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
updated a model 1 day ago
coolthor/comfyui-zimage-sulphur-nvfp4 updated a model 1 day ago
coolthor/MiniMax-H3-pruned-NVFP4 published a model 2 days ago
coolthor/MiniMax-H3-pruned-NVFP4Organizations
None yet
models 14
coolthor/comfyui-zimage-sulphur-nvfp4
Text-to-Image • Updated
coolthor/Huihui-Qwen3.6-35B-A3B-abliterated-FP8-DYNAMIC
Image-Text-to-Text • 36B • Updated • 401k • 4
coolthor/Laguna-S-2.1-attnQ8-DFlash-Q4-GGUF
Text Generation • 118B • Updated • 1.41k • 3
coolthor/Sulphur-2-distilled-Q4_K_M-GGUF
Text-to-Video • 21B • Updated • 2.29k
coolthor/gemma-4-12B-it-FP8-dynamic
Any-to-Any • 12B • Updated • 6.29k • 1
coolthor/Huihui-Qwen-AgentWorld-35B-A3B-abliterated-UD-Q3_K_M-GGUF
Text Generation • 35B • Updated • 318
coolthor/Huihui-gemma-4-26B-A4B-it-abliterated-FP8-Dynamic
Image-Text-to-Text • 27B • Updated • 37
coolthor/Huihui-Qwable-3.6-27b-abliterated-Q4_K_M-MTP-GGUF
27B • Updated • 410
coolthor/gemma-4-12B-it-NVFP4A16
Any-to-Any • 7B • Updated • 3.04k
datasets 0
None public yet