coolthor/Huihui-gemma-4-26B-A4B-it-abliterated-FP8-Dynamic
Image-Text-to-Text • 27B • Updated • 110
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 7 days ago
coolthor/Huihui-gemma-4-26B-A4B-it-abliterated-FP8-Dynamic updated a model 7 days ago
coolthor/Huihui-Qwable-3.6-27b-abliterated-Q4_K_M-MTP-GGUF updated a model 7 days ago
coolthor/Huihui-Qwen3.6-35B-A3B-abliterated-FP8-DYNAMICOrganizations
None yet
updated 4
models 7 days ago
published a
model 15 days ago
published a
model 29 days ago
updated 2
models about 1 month ago
published 2
models about 1 month ago
updated 4
models about 1 month ago
coolthor/Huihui-gemma-4-26B-A4B-it-abliterated-eagle3-draft
0.9B • Updated • 23 • 1
coolthor/Sulphur-2-distilled-NVFP4
Text-to-Video • Updated • 1.77k • 3
coolthor/Gemma-4-E4B-it-NVFP4A16
Image-Text-to-Text • 7B • Updated • 1.03k • 1
coolthor/Huihui-Qwen3.6-35B-A3B-abliterated-NVFP4-W4A4
Image-Text-to-Text • 21B • Updated • 184
published 2
models about 1 month ago
Model hallucinates
2
#1 opened about 2 months ago
by 
johnlockejrr
published a
model about 2 months ago
published a
model 2 months ago
liked a
model 2 months ago