RedHatAI/Inkling-FP8-block
Image-Text-to-Text • 952B • Updated • 51
AI & ML interests
OpenSource and AI
Recent Activity
Papers
SNLP: Layer-Parallel Inference via Structured Newton Corrections
S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation
RedHatAI/Inkling-FP8-dynamic
Image-Text-to-Text • 953B • Updated • 539
RedHatAI/Kimi-K2.6-NVFP4
Image-Text-to-Text • Updated • 7.71k • 13
RedHatAI/gemma-4-E2B-it
Any-to-Any • 5B • Updated • 320 • 1
RedHatAI/gemma-4-12B-it
Any-to-Any • 12B • Updated • 116
RedHatAI/gemma-4-12B-it-NVFP4
8B • Updated • 527k • 3
RedHatAI/gemma-4-12B-it-FP8-Dynamic
13B • Updated • 25k • 3
RedHatAI/gemma-4-26B-A4B-it
Image-Text-to-Text • 27B • Updated • 1.26k
RedHatAI/gemma-4-26B-A4B-it-NVFP4
Image-Text-to-Text • 15B • Updated • 1.15M • 38
RedHatAI/gemma-4-26B-A4B-it-FP8-dynamic
Image-Text-to-Text • 27B • Updated • 1.62M • 33
RedHatAI/gemma-4-31B-it-FP8-dynamic
Image-Text-to-Text • 33B • Updated • 367k • 23
RedHatAI/gemma-4-31B-it-NVFP4
Image-Text-to-Text • 20B • Updated • 1.36M • 54
RedHatAI/gemma-4-31B-it-FP8-block
Image-Text-to-Text • 31B • Updated • 6.03M • 40
RedHatAI/gemma-4-31B-it
Image-Text-to-Text • 33B • Updated • 600
RedHatAI/gemma-4-E4B-it
Any-to-Any • 8B • Updated • 5.67k
RedHatAI/Kimi-K2.6-FP8-BLOCK
Image-Text-to-Text • 1T • Updated • 4.07k • 4
RedHatAI/Llama-3_1-Nemotron-Ultra-253B-v1
Text Generation • 253B • Updated • 68
RedHatAI/Molmo2-4B
Image-Text-to-Text • 5B • Updated • 34
RedHatAI/Molmo2-8B
Image-Text-to-Text • 9B • Updated • 34
RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-speculator.dflash
3B • Updated • 98 • 1
RedHatAI/Hy3-NVFP4-FP8
Text Generation • 173B • Updated • 72
RedHatAI/GLM-5.2-NVFP4-FP8
Text Generation • 425B • Updated • 10.6k • 20
RedHatAI/gemma-4-31B
Image-Text-to-Text • 33B • Updated • 42
RedHatAI/gemma-4-26B-A4B
Image-Text-to-Text • 27B • Updated • 49
RedHatAI/Qwen3-30B-A3B-speculator.dflash
0.7B • Updated • 226
RedHatAI/GLM-5.2-NVFP4
Text Generation • 426B • Updated • 766 • 7
RedHatAI/GLM-5.2-NVFP4-FP8-mtp-FP8
10B • Updated • 378
RedHatAI/Qwen3.6-35B-A3B-NVFP4
20B • Updated • 2M • 163
RedHatAI/Qwen3.6-35B-A3B-FP8
Image-Text-to-Text • 36B • Updated • 13.3k
RedHatAI/Qwen3.6-35B-A3B-FP8-dynamic
Image-Text-to-Text • 35B • Updated • 24.5k • 5