-
Whisper Realtime Transcription (Gradio UI)
👂4Transcribe audio in realtime - Gradio UI version
-
DeepSeek R1 Distill Qwen 1.5B Demo Q8
🔥9DeepSeek R1 Distill Qwen 1.5B Demo GGUF(Q8) Fully in CPU
-
Chain of Draft: Thinking Faster by Writing Less
Paper • 2502.18600 • Published • 50 -
Llama-4-Maverick-17B Research
🏃88Llama-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 3 days ago
mradermacher/mistralai_Ministral-3-8B-Instruct-2512-abliterated-GGUF liked
a model 3 days ago
huihui-ai/Huihui-LFM2-8B-A1B-abliterated liked
a model 3 days ago
LiquidAI/LFM2-24B-A2B-GGUF Organizations
None yet
PAPERS
-
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper • 2412.13663 • Published • 161 -
A Survey of Small Language Models
Paper • 2410.20011 • Published • 46 -
No More Adam: Learning Rate Scaling at Initialization is All You Need
Paper • 2412.11768 • Published • 43 -
Chain of Draft: Thinking Faster by Writing Less
Paper • 2502.18600 • Published • 50
SMALL-TINY
A Collection of Small native Models
Image Creation
Good and working HF spaces to create images with Diffusion models
- Runtime errorFeatured2k
Stable Diffusion 3.5 Large
🏃2kGenerate images with SD3.5
- Running on ZeroFeatured9.4k
FLUX.1 [dev]
🖥9.4kGenerate images from your text prompt
- Running on ZeroFeatured5.05k
FLUX.1 [Schnell]
🏎5.05kGenerate images from text prompts instantly
- Running on Zero1.78k
DALLE 3 XL v2
🔥1.78kGenerate high‑resolution images from text prompts
Playgrounds
GRADIO examples
- Runtime error4
Whisper Realtime Transcription (Gradio UI)
👂4Transcribe audio in realtime - Gradio UI version
- Running9
DeepSeek R1 Distill Qwen 1.5B Demo Q8
🔥9DeepSeek R1 Distill Qwen 1.5B Demo GGUF(Q8) Fully in CPU
-
Chain of Draft: Thinking Faster by Writing Less
Paper • 2502.18600 • Published • 50 - Running88
Llama-4-Maverick-17B Research
🏃88Llama-4-Maverick-17B + Real Time Deep Research
Image Creation
Good and working HF spaces to create images with Diffusion models
- Runtime errorFeatured2k
Stable Diffusion 3.5 Large
🏃2kGenerate images with SD3.5
- Running on ZeroFeatured9.4k
FLUX.1 [dev]
🖥9.4kGenerate images from your text prompt
- Running on ZeroFeatured5.05k
FLUX.1 [Schnell]
🏎5.05kGenerate images from text prompts instantly
- Running on Zero1.78k
DALLE 3 XL v2
🔥1.78kGenerate high‑resolution images from text prompts
PAPERS
-
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper • 2412.13663 • Published • 161 -
A Survey of Small Language Models
Paper • 2410.20011 • Published • 46 -
No More Adam: Learning Rate Scaling at Initialization is All You Need
Paper • 2412.11768 • Published • 43 -
Chain of Draft: Thinking Faster by Writing Less
Paper • 2502.18600 • Published • 50
Playgrounds
SMALL-TINY
A Collection of Small native Models