Thomas Hill
945 posts
Thomas Hill
@TomAnswerAi
CEO and CoFounder https://t.co/eTZtlzfMyB a Shopify support automation tool
London เข้าร่วม Ağustos 2023
483 กำลังติดตาม88 ผู้ติดตาม
Sorry for the long wait, everyone! As I said, Qwen is going to keep open-sourcing!
Qwen@Alibaba_Qwen
⚡ Meet Qwen3.6-35B-A3B：Now Open-Source！🚀🚀 A sparse MoE model, 35B total params, 3B active. Apache 2.0 license. 🔥 Agentic coding on par with models 10x its active size 📷 Strong multimodal perception and reasoning ability 🧠 Multimodal thinking + non-thinking modes Efficient. Powerful. Versatile. Try it now👇 Blog：qwen.ai/blog?id=qwen3.… Qwen Studio：chat.qwen.ai HuggingFace：huggingface.co/Qwen/Qwen3.6-3… ModelScope：modelscope.cn/models/Qwen/Qw… API（‘Qwen3.6-Flash’ on Model Studio）：Coming soon～ Stay tuned
English
⚡ Meet Qwen3.6-35B-A3B：Now Open-Source！🚀🚀
A sparse MoE model, 35B total params, 3B active. Apache 2.0 license.
🔥 Agentic coding on par with models 10x its active size
📷 Strong multimodal perception and reasoning ability
🧠 Multimodal thinking + non-thinking modes
Efficient. Powerful. Versatile. Try it now👇
Blog：qwen.ai/blog?id=qwen3.…
Qwen Studio：chat.qwen.ai
HuggingFace：huggingface.co/Qwen/Qwen3.6-3…
ModelScope：modelscope.cn/models/Qwen/Qw…
API（‘Qwen3.6-Flash’ on Model Studio）：Coming soon～ Stay tuned
English
@1littlecoder I'm not leaving the house after they release that
English
I'm already scared about how dangerous it is going to be!
unusual_whales@unusual_whales
NEWS: Anthropic is preparing for the release of its new Opus 4.7 model, per the Information
English
MLX: there are far too many servers now: vMLX, oMLX, Osaurus, LMStudio, mlx-lm, mlx-vlm.
I will start some benchmarks now to figure out which one I'll use 🧐
English
Introducing a Visual Guide to Gemma 4 👀
An in-depth, architectural deep dive of the Gemma 4 family of models. From Per-Layer Embeddings to the vision and audio encoders. Take a look!
English
@Prince_Canuma Wow. I was interested to see some real well tests on this.
English
Just implemented Google’s TurboQuant in MLX and the results are wild!
Needle-in-a-haystack using Qwen3.5-35B-A3B across 8.5K, 32.7K, and 64.2K context lengths:
→ 6/6 exact match at every quant level
→ TurboQuant 2.5-bit: 4.9x smaller KV cache
→ TurboQuant 3.5-bit: 3.8x smaller KV cache
The best part: Zero accuracy loss compared to full KV cache.
Google Research@GoogleResearch
Introducing TurboQuant: Our new compression algorithm that reduces LLM key-value cache memory by at least 6x and delivers up to 8x speedup, all with zero accuracy loss, redefining AI efficiency. Read the blog to learn how it achieves these results: goo.gle/4bsq2qI
English
@Prince_Canuma yes same...And if you ever look at the wrong thing you are screwed for a few days after until it recalibrates 😬
English
@TomAnswerAi I tailor my algo by engaging with stuff I like and following only people of interest
English
This platform has the highest concentration of intelligence per capita I’ve ever seen.
It’s genuinely wild how smart and hardworking people are here🙌🏽
English
@TomAnswerAi ahh yeah -- good point. let me see what we can cook up here.
English
OpenGranola now runs 100% locally with Ollama. LLM suggestions, knowledge base embeddings, transcription — all on your Mac, nothing hits the network.
Just point it at Ollama instead of OpenRouter in settings and you're done.
github.com/yazinsai/OpenG…
yazin@yazins
Introducing: OpenGranola 🔥 I built an open source meeting copilot for macOS. It transcribes both sides of your call on-device, searches your own notes in real time, and hands you talking points right when the conversation needs them. No audio leaves your Mac. Point it at a folder of markdown files, pick any LLM through OpenRouter (Claude, GPT-4o, Gemini, Llama), and it just works. It's invisible to screen share too — nobody knows you have it. The whole thing is open source. Link below
English
Day-0 support on MLX for Mistral Small 4🚀
Congratulations to the @MistralAI team on the release.
Mistral AI for Developers@MistralDevs
🔥 Meet Mistral Small 4: One model to do it all. ⚡ 128 experts, 119B total parameters, 256k context window ⚡ Configurable Reasoning ⚡ Apache 2.0 ⚡ 40% faster, 3x more throughput Our first model to unify the capabilities of our flagship models into a single, versatile model.
English
gemini-3.1-flash-lite-preview is extremely underrated. I know I keep saying that, but nothing beats the (price*latency)/intelligence you get here.
English
@ivanfioravanti Great reco. Did not expect that amount cleaning!
English
One of the best Mac app ever!
Install it on all your machines!
I love it.
Tw93@HiTw93
🐹 Just shipped Mole V1.30.0. If you have cleaned tens of GB of junk from your Mac in one go, you know the feeling. Since October, Mole has gone from v1 to 30. This release improves reliability with safer orphan cleanup and better edge case handling. github.com/tw93/Mole
English
@miromind_ai Nice work! Agent side of things is a great area to be focused on 😎
English
🚀 Introducing MiroThinker-1.7 & MiroThinker-H1
Today, we release the latest generation of our research agent family: MiroThinker-1.7 and MiroThinker-H1.
Our goal is simple but ambitious: move beyond LLM chatbots to build heavy-duty, verifiable agents capable of solving real, critical tasks. Rather than merely scaling interaction turns, we focus on scaling effective interactions — improving both reasoning depth and step-level accuracy.
Key highlights:
🧠 Heavy-duty reasoning designed for long-horizon tasks
🔍 Verification-centric architecture with local and global verification
🌐 State-of-the-art performance on BrowseComp / BrowseComp-ZH / GAIA / Seal-0 research benchmarks
📊 Leading results across scientific and financial evaluation tasks
Explore MiroThinker:
Hugging Face: huggingface.co/collections/mi…
Github: github.com/MiroMindAI/Mir…
English
@patloeber @GoogleAIStudio Can never beat a nice visual demo like that.
English
Introducing Gemini Embedding 2! Our first multimodal embedding model for text, images, audio, video, and PDFs.
Here's an app you can try in @GoogleAIStudio where you can see multimodal search in action:
Logan Kilpatrick@OfficialLoganK
Say hello to Gemini Embedding 2, our new SOTA multimodal model that lets your bring text, images, video, audio, and docs into the same embedding space! 👀
English