-
4
Whisper Realtime Transcription (Gradio UI)
πTranscribe audio in realtime - Gradio UI version
-
7
DeepSeek R1 Distill Qwen 1.5B Demo Q8
π₯DeepSeek 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’ 49 -
85
Llama-4-Maverick-17B Research
πLlama-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
yeonseok-zeticai's
post
with π₯
about 8 hours ago
π NEW DROP: run your own on-device LLMβin minutes, on any phone
Today weβre open-sourcing everything you need to put Qwen3-0.6B straight into a production-ready mobile app:
π₯ Watch Qwen3-0.6B chat in real time on any smartphones!
π TPS benchmarks β slides comparing token-per-second across heterogeneous mobile devices
π» Plug-and-play source β Just Copy & Run the source to your project for Android (Kotlin & Java) and iOS (Swift).
π€ Cross-platform, one pipeline β ZETIC.MLange auto-tunes kernels for every different devices, weβve tested.
π¨βπ» Ready for production β swap in your own model, re-benchmark with one command, publish.
Get started
Just Sign-up and check the playground project, QWEN-0.6B
- https://mlange.zetic.ai/p/zetic-example/Qwen3-0.6B
We built this to show that cloud-free LLMs are ready today. Dive in, fork it, and tag ZETIC.ai when you launch your own on-device assistant, game NPC, or offline content generatorβweβll spotlight the best projects.
liked
a model
5 days ago
pyarn/bge-reranker-v2-m3-Q8_0-GGUF
liked
a model
5 days ago
pyarn/bge-reranker-v2-m3-Q5_K_M-GGUF
Organizations
None yet
Collections
5
Good and working HF spaces to create images with Diffusion models
spaces
9
Runtime error
Gemma3-1b-it GradioCHAT
π¦
Gradio Chatbot with Gemma 3 1B Instruct
Running
1
TweetGeneration
π
Gradio and HF free tools - from articles to tweets
Sleeping
Gemma2 2B Reflection
π
Sleeping
OuteWorlderAI LiteMistral150M
π
Sleeping
Gemma2 2B Instruct ST
π’
Runtime error
5
StableLM-Zepyhr-3B Playground
π
models
11

FM-1976/gemma-2b-docjoybot-lora-F16-GGUF
Updated
β’
15
β’
1

FM-1976/Gaia-LLM-8B-Q4_K_M-GGUF
Updated
β’
32
β’
1

FM-1976/Qwen-1.5B-Tweet-Generations-F16-GGUF
Updated
β’
19

FM-1976/SmolLM2-360M-it-llamafile
Text Generation
β’
Updated
β’
17

FM-1976/Qwen2.5-1.6b-llamafile
Text Generation
β’
Updated
β’
50
β’
1

FM-1976/Lite-Oute-1-300M-Instruct-openvino
Text Generation
β’
Updated
β’
10

FM-1976/stablelm-zephyr-3b-openvino-4bit
Updated
β’
7

FM-1976/ov_Llama-SmolTalk-3.2-1B-Instruct
Text Generation
β’
Updated
β’
18

FM-1976/ov_NuExtract-1.5-tiny
Text Generation
β’
Updated
β’
15

FM-1976/NuExtract-1.5-tiny-ONNX
Updated
β’
5
datasets
0
None public yet