A daemonic Ignoct commission piece for the lovely TinyLlama (2022)!
Ink, watercolour, gouache, and pencil on hot press paper
Ink, watercolour, gouache, and pencil on hot press paper
August 21, 2023 at 6:33 PM
A daemonic Ignoct commission piece for the lovely TinyLlama (2022)!
Ink, watercolour, gouache, and pencil on hot press paper
Ink, watercolour, gouache, and pencil on hot press paper
🚀 Looking for a powerful AI model that runs locally without requiring expensive hardware?
👉 Read the full review:
aiinovationhub.com/tinyllama-ed...
#TinyLlama #EdgeAI #ArtificialIntelligence #LLM #OpenSourceAI #LocalAI #MachineLearning #AIInnovation #AIReview #TechNews #AIInnovationHub
👉 Read the full review:
aiinovationhub.com/tinyllama-ed...
#TinyLlama #EdgeAI #ArtificialIntelligence #LLM #OpenSourceAI #LocalAI #MachineLearning #AIInnovation #AIReview #TechNews #AIInnovationHub
June 28, 2026 at 9:36 AM
🚀 Looking for a powerful AI model that runs locally without requiring expensive hardware?
👉 Read the full review:
aiinovationhub.com/tinyllama-ed...
#TinyLlama #EdgeAI #ArtificialIntelligence #LLM #OpenSourceAI #LocalAI #MachineLearning #AIInnovation #AIReview #TechNews #AIInnovationHub
👉 Read the full review:
aiinovationhub.com/tinyllama-ed...
#TinyLlama #EdgeAI #ArtificialIntelligence #LLM #OpenSourceAI #LocalAI #MachineLearning #AIInnovation #AIReview #TechNews #AIInnovationHub
I have written a basic server to make interaction easier; it is pretty much plug and play after running `python server.py`. If you wanna try it out, here is the repository, I‘m happy for any feedback :) It‘s just a bit rough atm 🤐
—> github.com/nathanlesage...
—> github.com/nathanlesage...
GitHub - nathanlesage/tinyllama: A wrapper for TinyLlama
A wrapper for TinyLlama. Contribute to nathanlesage/tinyllama development by creating an account on GitHub.
github.com
January 2, 2024 at 7:30 PM
I have written a basic server to make interaction easier; it is pretty much plug and play after running `python server.py`. If you wanna try it out, here is the repository, I‘m happy for any feedback :) It‘s just a bit rough atm 🤐
—> github.com/nathanlesage...
—> github.com/nathanlesage...
the LLM is open source, no tokens needed, makes the prototype easy to share and realistic
mlvoca.github.io/free-llm-api/
mlvoca.github.io/free-llm-api/
Free LLM API - mlvoca.com
Generate text using free AI models like TinyLlama and DeepSeek R1. No API key required, easy integration.
mlvoca.github.io
July 28, 2025 at 10:51 PM
the LLM is open source, no tokens needed, makes the prototype easy to share and realistic
mlvoca.github.io/free-llm-api/
mlvoca.github.io/free-llm-api/
We have four runnable, vulnerable LLM apps: Python with Apertus 8B, .NET with Phi-3 ONNX, and TypeScript and Java with TinyLlama plus a LoRA adapter.
August 9, 2026 at 11:48 PM
We have four runnable, vulnerable LLM apps: Python with Apertus 8B, .NET with Phi-3 ONNX, and TypeScript and Java with TinyLlama plus a LoRA adapter.
Free AI Chat, locally in your browser. 💻
- No signup required
- 100% data privacy
- No API keys 🔒
Supported Models:
• #SmolLM2
• #Qwen
• #Llama
• #DeepSeek R1
• #Phi
• #TinyLlama
• & More
🔗 zalt.me/tools/free-a...
#FreeAI #Free #WebGPU #AI #WebLLM #ChatGPT #JS #OpenSource #LLM #Chrome
- No signup required
- 100% data privacy
- No API keys 🔒
Supported Models:
• #SmolLM2
• #Qwen
• #Llama
• #DeepSeek R1
• #Phi
• #TinyLlama
• & More
🔗 zalt.me/tools/free-a...
#FreeAI #Free #WebGPU #AI #WebLLM #ChatGPT #JS #OpenSource #LLM #Chrome
June 30, 2026 at 2:59 AM
If someone wants to get the ChatGPT experience locally on your computer as well, I have now set up a repository with my code for TinyLlama. This gives you a quick start into it. You only need to clone, set up a Python environment, and run `python server.py`
See more here: github.com/nathanlesage...
See more here: github.com/nathanlesage...
GitHub - nathanlesage/tinyllama: A wrapper for TinyLlama
A wrapper for TinyLlama. Contribute to nathanlesage/tinyllama development by creating an account on GitHub.
github.com
January 2, 2024 at 9:14 PM
If someone wants to get the ChatGPT experience locally on your computer as well, I have now set up a repository with my code for TinyLlama. This gives you a quick start into it. You only need to clone, set up a Python environment, and run `python server.py`
See more here: github.com/nathanlesage...
See more here: github.com/nathanlesage...
testing #Phi3, #TinyLlama and #Llama3 models on #raspberrypi using #ollama pimylifeup.com/raspberry-pi...
#LLM #SLM #AI #GenAI #Iot #EdgeAI
#LLM #SLM #AI #GenAI #Iot #EdgeAI
How to run Ollama on the Raspberry Pi
Easily run large language models on the Pi
pimylifeup.com
April 26, 2024 at 2:20 PM
testing #Phi3, #TinyLlama and #Llama3 models on #raspberrypi using #ollama pimylifeup.com/raspberry-pi...
#LLM #SLM #AI #GenAI #Iot #EdgeAI
#LLM #SLM #AI #GenAI #Iot #EdgeAI
I made a small reflection & journalling app that runs on your computer and asks you reflective questions about your feelings: github.com/astrosnat/ti...
GitHub - astrosnat/tinyreflections: A reflection & journaling app using tinyllama
A reflection & journaling app using tinyllama. Contribute to astrosnat/tinyreflections development by creating an account on GitHub.
github.com
October 3, 2024 at 9:08 AM
I made a small reflection & journalling app that runs on your computer and asks you reflective questions about your feelings: github.com/astrosnat/ti...
Day 23 of #100DaysOfCode
I had limited time to work on my challenge today. But, I wrote a simple #Ollama usage guide 👇
github.com/sinocelt/100...
#HireMe #JobSeeker #DataScience #portfolio #AI #LLM #AI #TinyLlama
I had limited time to work on my challenge today. But, I wrote a simple #Ollama usage guide 👇
github.com/sinocelt/100...
#HireMe #JobSeeker #DataScience #portfolio #AI #LLM #AI #TinyLlama
August 16, 2025 at 6:46 AM
Day 23 of #100DaysOfCode
I had limited time to work on my challenge today. But, I wrote a simple #Ollama usage guide 👇
github.com/sinocelt/100...
#HireMe #JobSeeker #DataScience #portfolio #AI #LLM #AI #TinyLlama
I had limited time to work on my challenge today. But, I wrote a simple #Ollama usage guide 👇
github.com/sinocelt/100...
#HireMe #JobSeeker #DataScience #portfolio #AI #LLM #AI #TinyLlama
a selfhosted verison of TinyLlama Chat 1.1B Q4
February 1, 2025 at 9:52 AM
a selfhosted verison of TinyLlama Chat 1.1B Q4
Testing TinyLLaMA and I'm in awe
December 31, 2023 at 1:23 PM
Testing TinyLLaMA and I'm in awe
Yes sorry. Thanks for your return. Will try TinyLlama and distillBert.
September 11, 2025 at 1:23 PM
Yes sorry. Thanks for your return. Will try TinyLlama and distillBert.
And how does this apply to synthetic data? For example, if I generate some training data with Falcon (manipulating it, filtering it, running through multiple evaluation steps to improve it, etc until I'm happy with it), and then use that to train TinyLlama... how do they expect me to source THAT?
December 9, 2023 at 2:41 AM
And how does this apply to synthetic data? For example, if I generate some training data with Falcon (manipulating it, filtering it, running through multiple evaluation steps to improve it, etc until I'm happy with it), and then use that to train TinyLlama... how do they expect me to source THAT?
You *can* get down to esp32 level.
You can run a SLM on an 8$ microprocessor, and it'll happily generate text.
You won't mistake it for anything more than a gpt 1 though.
(Using TinyLlama, we're talking less than 5m parameters.)
You can run a SLM on an 8$ microprocessor, and it'll happily generate text.
You won't mistake it for anything more than a gpt 1 though.
(Using TinyLlama, we're talking less than 5m parameters.)
September 22, 2026 at 12:40 AM
You *can* get down to esp32 level.
You can run a SLM on an 8$ microprocessor, and it'll happily generate text.
You won't mistake it for anything more than a gpt 1 though.
(Using TinyLlama, we're talking less than 5m parameters.)
You can run a SLM on an 8$ microprocessor, and it'll happily generate text.
You won't mistake it for anything more than a gpt 1 though.
(Using TinyLlama, we're talking less than 5m parameters.)
tinyllama on 1.5gb of vram was already 3 years ago
May 5, 2026 at 2:08 PM
tinyllama on 1.5gb of vram was already 3 years ago
Yeah, if they mean it has to be impossible, well, good luck with that.
And re: sourcing, often *you don't know*. For example, if I train a model on a foundation of TinyLlama, Mistral or Falcon (my go-tos due to their permissive licensing), I don't know what THEY used, only what *I* used atop them.
And re: sourcing, often *you don't know*. For example, if I train a model on a foundation of TinyLlama, Mistral or Falcon (my go-tos due to their permissive licensing), I don't know what THEY used, only what *I* used atop them.
December 9, 2023 at 2:40 AM
Yeah, if they mean it has to be impossible, well, good luck with that.
And re: sourcing, often *you don't know*. For example, if I train a model on a foundation of TinyLlama, Mistral or Falcon (my go-tos due to their permissive licensing), I don't know what THEY used, only what *I* used atop them.
And re: sourcing, often *you don't know*. For example, if I train a model on a foundation of TinyLlama, Mistral or Falcon (my go-tos due to their permissive licensing), I don't know what THEY used, only what *I* used atop them.
That is a great dataset for fine tuning or RAG but nowhere near enough to train a model from scratch. TinyLlama - github.com/jzhang38/Tin... - is an open model trained on an open dataset consisting of 3T tokens (about 2T words) and it's not really usable.
GitHub - jzhang38/TinyLlama: The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens. - jzhang38/TinyLlama
github.com
December 15, 2024 at 11:18 PM
That is a great dataset for fine tuning or RAG but nowhere near enough to train a model from scratch. TinyLlama - github.com/jzhang38/Tin... - is an open model trained on an open dataset consisting of 3T tokens (about 2T words) and it's not really usable.
Oh god I'm building a TinyLlama X86 and I have a Roland MT-32. No one has an accurate recording of how freaking awesome Mortal Kombat DOS sounded on Midi hardware. I am going to make a good recording of it.
February 5, 2025 at 6:44 PM
Oh god I'm building a TinyLlama X86 and I have a Roland MT-32. No one has an accurate recording of how freaking awesome Mortal Kombat DOS sounded on Midi hardware. I am going to make a good recording of it.
After playing with TinyLlama for a few days, I am convinced that this is huge: it looks and feels like ChatGPT despite being open weight, and a minuscule fraction of its size. It can run locally, produces fair results, and is hands down a joy to play around with.
January 2, 2024 at 7:23 PM
After playing with TinyLlama for a few days, I am convinced that this is huge: it looks and feels like ChatGPT despite being open weight, and a minuscule fraction of its size. It can run locally, produces fair results, and is hands down a joy to play around with.
Seen it, used it, liked it. TinyLlama still seems to work better for me.
March 14, 2025 at 8:20 AM
Seen it, used it, liked it. TinyLlama still seems to work better for me.
2026年最新！小型LLM日本語ガチランキング【Qwen3 vs Gemma3 vs TinyLlama】Ollamaで爆速カスタム術も
https://zenn.dev/kewa8579/articles/2996512cafaec4
https://zenn.dev/kewa8579/articles/2996512cafaec4
2026年最新！小型LLM日本語ガチランキング【Qwen3 vs Gemma3 vs TinyLlama】Ollamaで爆速カスタム術も
zenn.dev
January 18, 2026 at 6:41 PM
2026年最新！小型LLM日本語ガチランキング【Qwen3 vs Gemma3 vs TinyLlama】Ollamaで爆速カスタム術も
https://zenn.dev/kewa8579/articles/2996512cafaec4
https://zenn.dev/kewa8579/articles/2996512cafaec4
🔥 Hot Repo！ 🔥 (100+ new stars)
📦 jzhang38 / TinyLlama
⭐ 4,689 (+108)
🗒 Python
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
📦 jzhang38 / TinyLlama
⭐ 4,689 (+108)
🗒 Python
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
GitHub - jzhang38/TinyLlama: The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens. - GitHub - jzhang38/TinyLlama: The TinyLlama project is an open endeavor to pretrain a 1.1B Llama mode...
github.com
January 8, 2024 at 1:50 AM