-
Whisper Realtime Transcription (Gradio UI)
π4Transcribe audio in realtime - Gradio UI version
-
DeepSeek R1 Distill Qwen 1.5B Demo Q8
π₯8DeepSeek R1 Distill Qwen 1.5B Demo GGUF(Q8) Fully in CPU
-
Chain of Draft: Thinking Faster by Writing Less
Paper β’ 2502.18600 β’ Published β’ 50 -
Llama-4-Maverick-17B Research
π88Llama-4-Maverick-17B + Real Time Deep Research
Matricardi Fabio
FM-1976
AI & ML interests
control system engineering, AI, LLM with python. ThePoorGPUguy on substack
Recent Activity
liked
a model
about 7 hours ago
nvidia/parakeet-tdt-0.6b-v3
liked
a model
about 7 hours ago
UsefulSensors/moonshine
liked
a model
about 7 hours ago
shoumenchougou/RWKV7-G1a-0.1B-GGUF
Organizations
None yet
PAPERS
-
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper β’ 2412.13663 β’ Published β’ 158 -
A Survey of Small Language Models
Paper β’ 2410.20011 β’ Published β’ 46 -
No More Adam: Learning Rate Scaling at Initialization is All You Need
Paper β’ 2412.11768 β’ Published β’ 43 -
Chain of Draft: Thinking Faster by Writing Less
Paper β’ 2502.18600 β’ Published β’ 50
SMALL-TINY
A Collection of Small native Models
-
vicgalle/gpt2-alpaca-gpt4
Text Generation β’ 0.1B β’ Updated β’ 1.02k β’ 23 -
andreaskoepf/pythia-1.4b-gpt4all-pretrain
Text Generation β’ Updated β’ 27 β’ 7 -
EleutherAI/pythia-1b
Text Generation β’ 1B β’ Updated β’ 36.5k β’ 42 -
EleutherAI/pythia-410m-deduped
Text Generation β’ 0.5B β’ Updated β’ 29.8k β’ 20
Image Creation
Good and working HF spaces to create images with Diffusion models
-
Running on ZeroFeatured1.96k
Stable Diffusion 3.5 Large
π1.96kGenerate images with SD3.5
-
Running on ZeroFeatured9.31k
FLUX.1 [dev]
π₯9.31kGenerate images from text prompts
-
Running on ZeroFeatured5k
FLUX.1 [Schnell]
π5kGenerate images from text prompts
-
Running on Zero1.78k
DALLE 3 XL v2
π₯1.78kGenerate images from text prompts
Playgrounds
GRADIO examples
-
Runtime error4
Whisper Realtime Transcription (Gradio UI)
π4Transcribe audio in realtime - Gradio UI version
-
Running8
DeepSeek R1 Distill Qwen 1.5B Demo Q8
π₯8DeepSeek R1 Distill Qwen 1.5B Demo GGUF(Q8) Fully in CPU
-
Chain of Draft: Thinking Faster by Writing Less
Paper β’ 2502.18600 β’ Published β’ 50 -
Running88
Llama-4-Maverick-17B Research
π88Llama-4-Maverick-17B + Real Time Deep Research
Image Creation
Good and working HF spaces to create images with Diffusion models
-
Running on ZeroFeatured1.96k
Stable Diffusion 3.5 Large
π1.96kGenerate images with SD3.5
-
Running on ZeroFeatured9.31k
FLUX.1 [dev]
π₯9.31kGenerate images from text prompts
-
Running on ZeroFeatured5k
FLUX.1 [Schnell]
π5kGenerate images from text prompts
-
Running on Zero1.78k
DALLE 3 XL v2
π₯1.78kGenerate images from text prompts
PAPERS
-
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper β’ 2412.13663 β’ Published β’ 158 -
A Survey of Small Language Models
Paper β’ 2410.20011 β’ Published β’ 46 -
No More Adam: Learning Rate Scaling at Initialization is All You Need
Paper β’ 2412.11768 β’ Published β’ 43 -
Chain of Draft: Thinking Faster by Writing Less
Paper β’ 2502.18600 β’ Published β’ 50
Playgrounds
SMALL-TINY
A Collection of Small native Models
-
vicgalle/gpt2-alpaca-gpt4
Text Generation β’ 0.1B β’ Updated β’ 1.02k β’ 23 -
andreaskoepf/pythia-1.4b-gpt4all-pretrain
Text Generation β’ Updated β’ 27 β’ 7 -
EleutherAI/pythia-1b
Text Generation β’ 1B β’ Updated β’ 36.5k β’ 42 -
EleutherAI/pythia-410m-deduped
Text Generation β’ 0.5B β’ Updated β’ 29.8k β’ 20