RedHatAI/Kimi-K3-speculator.dspark
5B • Updated • 5 • 2
AI & ML interests
OpenSource and AI
Recent Activity
View all activity
Papers
SNLP: Layer-Parallel Inference via Structured Newton Corrections
S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation
RedHatAI/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Text Generation • 32B • Updated
RedHatAI/Muse-Glimmer-30B-W4A16
8B • Updated • 2
RedHatAI/Muse-Glimmer-30B
Image-Text-to-Text • 30B • Updated
RedHatAI/Muse-Glimmer-30B-NVFP4
19B • Updated • 13
RedHatAI/Muse-Glimmer-30B-FP8-block
Image-Text-to-Text • 30B • Updated • 8
RedHatAI/Ministral-3-14B-Instruct-2512-BF16
14B • Updated
RedHatAI/granite-4.1-8b-fp8
Text Generation • 9B • Updated
RedHatAI/granite-4.1-8b
Text Generation • 9B • Updated
RedHatAI/privacy-filter
Token Classification • 1B • Updated
RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-quantized.w4a16
Text Generation • 561B • Updated • 693 • 3
RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-block
Text Generation • 561B • Updated • 4.62k
RedHatAI/Mistral-Medium-3.5-128B
Image-Text-to-Text • 128B • Updated • 266
RedHatAI/diffusiongemma-26B-A4B-it-NVFP4
Image-Text-to-Text • 26B • Updated • 192k • 19
RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic
Image-Text-to-Text • 26B • Updated • 26.4k • 11
RedHatAI/Qwen3-VL-30B-A3B-Instruct
Image-Text-to-Text • 31B • Updated • 690
RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
Text Generation • 303B • Updated • 82
RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-dynamic
Text Generation • 561B • Updated • 2.64k • 1
RedHatAI/Qwen3.6-35B-A3B
Image-Text-to-Text • 36B • Updated • 1.63k
RedHatAI/Qwen3.6-35B-A3B-FP8
Image-Text-to-Text • 36B • Updated • 7.7k
RedHatAI/Qwen3.6-35B-A3B-NVFP4
Image-Text-to-Text • 35B • Updated • 1.75M • 170
RedHatAI/GLM-5.2-FP8
Text Generation • 753B • Updated • 94
RedHatAI/gemma-4-12B-it-NVFP4
Any-to-Any • 13B • Updated • 360k • 4
RedHatAI/gemma-4-12B-it-FP8-Dynamic
Any-to-Any • 13B • Updated • 13.6k • 4
RedHatAI/gemma-4-E4B-it
Any-to-Any • 8B • Updated • 2.82k • 1
RedHatAI/gemma-4-26B-A4B-it
Image-Text-to-Text • 26B • Updated • 3.15k
RedHatAI/gemma-4-26B-A4B-it-FP8-dynamic
Image-Text-to-Text • 27B • Updated • 1.09M • 38
RedHatAI/gemma-4-26B-A4B-it-NVFP4
Image-Text-to-Text • 26B • Updated • 684k • 39
RedHatAI/gemma-4-31B-it
Image-Text-to-Text • 31B • Updated • 801
RedHatAI/gemma-4-31B-it-FP8-block
Image-Text-to-Text • 31B • Updated • 3.37M • 44