sleepyeldrazi/Nemotron-3.5-Lightning-30B-A3B-REAP-20B
Text Generation • 20B • Updated • 535
Kaloyan Nikolov
sleepyeldrazi
·
AI & ML interests
ML engineer working on LLM inference and training. Finalizing my M.Sc. Computer Science @ RWTH Aachen.
Currently focusing on DGX Spark models/frameworks. Contact: konik98@gmail.com
Recent Activity
new activity about 10 hours ago
Qwen/Qwen3.8-27B:Exploring ThinkingCap fine-tunes for Qwen 3.8: Is it still necessary with native `reasoning_effort`? new activity 2 days ago
Qwen/Qwen3.8-27B:How can I run this well on an RTX 5070 ti? liked a model 2 days ago
Qwen/Qwen3.6-27BOrganizations
None yet
models 10
sleepyeldrazi/Nemotron-3.5-Lightning-30B-A3B-REAP-20B-LoRA-IQ4NL
Text Generation • 20B • Updated • 377
sleepyeldrazi/DeepSeek-v4-Flash-REAP-K150-NVFP4
Text Generation • 178B • Updated • 39
sleepyeldrazi/DeepSeek-v4-Flash-REAP-K180-NVFP4
Text Generation • 208B • Updated • 345 • 2
sleepyeldrazi/DeepSeek-v4-Flash-REAP-K128-NVFP4
Text Generation • 155B • Updated • 483 • 5
sleepyeldrazi/deepseek-v4-flash-reap-k128-Q2-Q4-Mixed-GGUF
Text Generation • 155B • Updated • 1.11k • 3
sleepyeldrazi/deepseek-v4-flash-reap-k128-Q2-GGUF
Text Generation • 155B • Updated • 1.67k • 7
sleepyeldrazi/Qwen3.5-9B-MXFP4-MTP
Image-Text-to-Text • 2B • Updated • 136 • 1
sleepyeldrazi/Qwen3.5-4B-MXFP4-MTP
Image-Text-to-Text • 0.8B • Updated • 83 • 1
sleepyeldrazi/Qwen3.6-27B-MXFP4-MTP
Image-Text-to-Text • 6B • Updated • 68 • 1