Steffen Röcker PRO

sroecker's activity

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

liked 2 models 3 days ago

mistralai/Mistral-Small-4-119B-2603-eagle

Updated 3 days ago • 188 • 31

mistralai/Mistral-Small-4-119B-2603

119B • Updated 3 days ago • 5.36k • 250

upvoted an article 7 days ago

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

10 days ago

•

66

liked a model 7 days ago

nvidia/Kimi-K2.5-Thinking-Eagle3

Text Generation • Updated 8 days ago • 395 • 10

liked a model 8 days ago

Tesslate/OmniCoder-9B

Text Generation • Updated 7 days ago • 12.2k • 326

upvoted a collection 9 days ago

Distil Efficiency Benchmarks

Collection

Collection of models used in the blog post www.distillabs.ai/blog/the-10x-inference-tax-you-dont-have-to-pay • 9 items • Updated 18 days ago • 3

liked 2 models 15 days ago

RedHatAI/MiniMax-M2.5

Text Generation • 229B • Updated 9 days ago • 136 • 1

EganAI/qwen3.5-9b-terminal-merge

Text Generation • 9B • Updated 2 days ago • 3.78k • 15

liked a model 17 days ago

Ex0bit/Qwen3.5-PRISM-Dynamic-Quant-GGUF

Text Generation • 0.8B • Updated 17 days ago • 3.26k • 6

liked 2 models 19 days ago

lyraaaa/baguettotron-SAE-L48-8x-k16-774m

Updated 19 days ago • 2

kaitchup/Qwen3.5-27B-autoround-W4A16

7B • Updated 20 days ago • 2.54k • 8

upvoted a collection 19 days ago

Quantized Qwen3.5

Collection

Verified models. Compatible with Transformers v5.3 and vLLM v0.16.1rc1 (nightly). Under evaluation. • 9 items • Updated 7 days ago • 9

liked a model 20 days ago

huihui-ai/Huihui-LFM2-24B-A2B-abliterated

Text Generation • Updated 20 days ago • 625 • 8

liked a model 21 days ago

huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated

Image-Text-to-Text • 36B • Updated 18 days ago • 50.2k • 225

liked a model 23 days ago

bknyaz/Qwen3-Coder-Next-REAM

Text Generation • 60B • Updated Feb 11 • 781 • 28

upvoted 2 collections 23 days ago

Qwen3-MoE

Collection

Compressed Qwen3 MoE models with a reduced number of experts. See additional models at https://huggingface.co/bknyaz. • 9 items • Updated Feb 11 • 3

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated 23 days ago • 132

liked 3 datasets 23 days ago

peteromallet/dataclaw-peteromallet

Viewer • Updated 22 days ago • 549 • 9.98k • 295

crozai/croz-infbench-sharegpt

Viewer • Updated Mar 26, 2025 • 394 • 27 • 1

crozai/croz-coding-sharegpt

Viewer • Updated Mar 26, 2025 • 118k • 10 • 1