-
mradermacher/Qwen3.8-27B-Uncensored-FP8-i1-GGUF
27B • Updated • 2.35k • 3 -
orcarouter/Qwen3.8-27B-Uncensored-FP8
Image-Text-to-Text • 28B • Updated • 121k • 1.86k -
orcarouter/Qwen3.8-Flash-Next-Uncensored-FP8
Image-Text-to-Text • 180B • Updated • 117k • 60 -
chimingw/Qwen3.8-27B-Uncensored-OrcaRouter-MLX-6bit
Image-Text-to-Text • 28B • Updated • 931 • 2
Felix Tuma
floom
AI & ML interests
NLP
Recent Activity
upvoted a paper 12 days ago
Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents liked a Space about 2 months ago
Qwen/Qwen3-TTS updated a collection about 2 months ago
LocalModelsOrganizations
None yet
-
EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering
Paper • 2509.25175 • Published • 31 -
From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones
Paper • 2509.25123 • Published • 22 -
SCI-Verifier: Scientific Verifier with Thinking
Paper • 2509.24285 • Published • 10
-
mradermacher/Qwen3.8-27B-Uncensored-FP8-i1-GGUF
27B • Updated • 2.35k • 3 -
orcarouter/Qwen3.8-27B-Uncensored-FP8
Image-Text-to-Text • 28B • Updated • 121k • 1.86k -
orcarouter/Qwen3.8-Flash-Next-Uncensored-FP8
Image-Text-to-Text • 180B • Updated • 117k • 60 -
chimingw/Qwen3.8-27B-Uncensored-OrcaRouter-MLX-6bit
Image-Text-to-Text • 28B • Updated • 931 • 2
-
EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering
Paper • 2509.25175 • Published • 31 -
From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones
Paper • 2509.25123 • Published • 22 -
SCI-Verifier: Scientific Verifier with Thinking
Paper • 2509.24285 • Published • 10
models 0
None public yet
datasets 0
None public yet