Ryan Susman PRO

darkmatter2222's activity

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

New activity in poolside/Laguna-XS-2.1 1 day ago

Thank you for the model! Hope to see it outperform Qwen!

#6 opened 1 day ago by

darkmatter2222

New activity in GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF 1 day ago

Bro... Benchmarks!

🔥👍 3

1

#2 opened 1 day ago by

darkmatter2222

New activity in InternScience/Agents-A1 1 day ago

Software Development Benchmarks please! and Congrats! Too good to be true?

1

#23 opened 1 day ago by

darkmatter2222

How does it compare to Ornith, Qwen AgentWorld, Qwen 3.6 27B?

3

#22 opened 3 days ago by

jjaksic

New activity in migtissera/Tess-4-27B 2 days ago

This has promise.

#10 opened 2 days ago by

darkmatter2222

New activity in empero-ai/Qwythos-9B-v2 3 days ago

Can we get a Qwythos-Code please!

👍 1

1

#2 opened 3 days ago by

darkmatter2222

Congratulations on the new release! #OpenSource!

❤️ 4

#1 opened 3 days ago by

darkmatter2222

New activity in nvidia/Qwen3.6-27B-NVFP4 6 days ago

Does it support MTP?

➕👍 3

4

#6 opened 14 days ago by

sharon8811

New activity in nvidia/Qwen3.6-27B-NVFP4 7 days ago

doubled TPS NVFP4 vs FP8

🔥 4

3

#15 opened 12 days ago by

sSeeMyRolexXx

[need help] vllm 0.24.0 on dgx spark warn Your GPU does not have native support for FP4

➕ 1

3

#16 opened 12 days ago by

imshenshen

New activity in nvidia/Qwen3.6-27B-NVFP4 13 days ago

Works via Ollama, but the ~40 tok/s MTP speedup requires raw llama-server (Ollama has no --spec-type flag) - plus vLLM lockup findings on DGX Spark

1

#11 opened 13 days ago by

darkmatter2222

liked a model 13 days ago

nvidia/Qwen3.6-27B-NVFP4

Text Generation • 18B • Updated 14 days ago • 1.15M • 355

New activity in nvidia/Qwen3.6-27B-NVFP4 13 days ago

will it work on rtx 5090 32gb vram ?

10

#5 opened 14 days ago by

arunsahu44

Why does this say 18B?

1

#9 opened 13 days ago by

darkmatter2222

New activity in empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF 14 days ago

For all the Qwythos models, can we get Speculative Decoding layers please!

2

#15 opened 14 days ago by

darkmatter2222

New activity in deepreinforce-ai/Ornith-1.0-35B-GGUF 18 days ago

Disappointed. Terrible for Agentic Coding Harness

5

#9 opened 18 days ago by

darkmatter2222

New activity in deepreinforce-ai/Ornith-1.0-397B-FP8 18 days ago

#excited

3

#1 opened 18 days ago by

darkmatter2222

New activity in zai-org/GLM-5.2 22 days ago

GLM-5.2-Flash 20B -40B would be amazing.

🔥 28

6

#15 opened 24 days ago by

UniversalLove333

New activity in nvidia/LocateAnything-3B about 1 month ago

This is the greatest release since GPT 3.5, 'Self Automating Machines'

7

#9 opened about 1 month ago by

darkmatter2222

liked a Space 10 months ago

Running on Zero

Agents

824

IndexTTS 2 Demo

🏢

824

Generate expressive speech from text with voice and emotion control