-
Whisper Realtime Transcription (Gradio UI)
👂4Transcribe audio in realtime - Gradio UI version
-
DeepSeek R1 Distill Qwen 1.5B Demo Q8
🔥8DeepSeek 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
reacted
to
wangbuer999's
post
with 🔥
about 3 hours ago
HunyuanImage 3.0-Instruct just dropped
fresh -sourceImage 3.0model! Spent 20 mins testing it on a Messi + retro scrambler fusion case
Ran on diffusers v0.26.3 + CUDA 12.1 | 8B MoE params (1.3B activated) | zero VRAM issues
strength=0.9 Messi #10 kit/tattoo sharp, moto’s rusted metal texture blurred (classic open-source pain)
strength=0.7 Moto/cobblestone background crisp, Messi’s jersey details faded completely
strength=0.75 + prompt "Blend seamlessly, keep all original details": both subject & background sharp
No ControlNet, no manual masking the model’s chain-of-thought reasoning parses image+prompt first
Already outperforms Qwen-Image-Edit 2511 (GSB eval +25.7% on single-image edits) | 100% open-source
👉 Repo: https://hunyuan.tencent.com/chat/HunyuanDefault?from=modelSquare&modelId=Hunyuan-Image-3.0-Instruct
technical report：https://arxiv.org/abs/2509.23951
Anyone else struggled with strength tweaks for fusion? This fixed it for my Messi+moto case did it work as well for yours?
liked
a model
1 day ago
amd/Qwen-2.5_1.5B_Instruct-onnx-ryzenai-1.7-hybrid
liked
a model
1 day ago
byteshape/Qwen3-30B-A3B-Instruct-2507-GGUF
Organizations
None yet
-
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper • 2412.13663 • Published • 159 -
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
A Collection of Small native Models
-
Whisper Realtime Transcription (Gradio UI)
👂4Transcribe audio in realtime - Gradio UI version
-
DeepSeek R1 Distill Qwen 1.5B Demo Q8
🔥8DeepSeek 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
Good and working HF spaces to create images with Diffusion models
-
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper • 2412.13663 • Published • 159 -
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
A Collection of Small native Models