Abhilash Sulibela

killSwitch1869's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in InternScience/Agents-A1 17 days ago

MTP / DFlash support?

🚀👀 3

1

#16 opened 17 days ago by

killSwitch1869

New activity in nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 about 1 month ago

Can't run on dgx spark with vllm

3

#33 opened about 2 months ago by

moranilt

New activity in r0b0tlab/nex-n2-mini-nvfp4 about 1 month ago

GB10 vLLM recipe / config?

#2 opened about 1 month ago by

killSwitch1869

upvoted a collection about 1 month ago

Inference Optimized Checkpoints (with Model Optimizer)

Collection

A collection of generative models quantized and optimized for inference with Model Optimizer. • 84 items • Updated about 22 hours ago • 183

liked a model about 1 month ago

michaelw9999/Qwopus3.6-27B-v2-MTP-NVFP4-GGUF

27B • Updated Jun 10 • 78.9k • 10

New activity in Jackrong/Qwopus3.6-27B-v2-MTP-GGUF about 1 month ago

Please do mtp model that are compatible with vllm

➕ 2

2

#6 opened about 2 months ago by

FRancoissss

Any plans to release an NVFP4 version?

3

#1 opened 2 months ago by

Rubrigate

upvoted a collection about 1 month ago

🚀 Qwen-MTP

Collection

⚡ MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy. • 9 items • Updated 24 days ago • 34