Robert (@Gattic) header
Robert (@Gattic) profile picture

Programmer 20 years | Local AI | Open Source - https://teapawt.org/t.co/sxbtuqgppL - Prev FactSet (FDS)

Joined November 2011
Pinned Tweet
Here is my first article which talks about how I am running DeepSeek on two of my DGX Sparks: gattic.com/articles/two-dgx-… More articles to come! If you have any topics you would like me to write about, let me know!
1
1
11
379
Hello, Google
2
3
56
So how much of the GTA 6 map has everyone explored already?
4
5
93
I am really excited about Hy4. I am just surprised at its size...
⚖️ Tencent gave the Local AI crowd a 770B to figure out how to run! 😬And the smallest published GGUF is only ~215 GiB. Can we squeeze it onto a DGX Spark? The weights are finally here! Tencent (@TencentHunyuan) released its flagship Hy4 open weights, and AngelSlim already has 3x GGUF quantizations available. Here are the model stats as a refresher 🧠 770B total parameters ⚡ 49B active per text token 📚 1 MILLION token context 👁️ Native multimodal architecture 🖥️ GUI and computer use 🎮 Unreal, Unity, Godot, Blender and CAD workflows 🚀 Built-in 3.3B DFly2 speculative drafter GGUF sizes! 💾 Q4_K_M → 437.93 GiB 💾 IQ2 → 309.58 GiB 🔥 STQ1_0 → 214.65 GiB 👈 that smallest version averages just 2.39 bits per weight! 🍎 Mac Studio M5 Ultra, 512GB unified RAM → Enough capacity for the Q4 weights on paper. 🍎 256GB Mac Studio → Potentially enough memory for the aggressive STQ1_0 version. 🟢 4× DGX Spark, 128GB each → 512GB combined memory, but distributed inference support is required. And here's an interesting economic comparison. 512GB Mac Studio → $22,299 4× DGX Spark at $6,950 → $27,800 💰 Difference → $5,501 The STQ1_0 quant also requires a custom llama.cpp patch, and its coding/reasoning quality needs testing. ⚠️ Licensed under Tencent Hy License, not plain Apache 2.0. Links in ALT.
5
59
Seems people waited over a decade for hot garbage. I hope GTA 6 can be saved
2
3
96
Short highlights video of my interview with @coinbase @base @baseapac is live on my YT channel Was a pleasure to sit down with @Nibel_eth and talk about how my biggest L ended up as the biggest push in my crypto journey. It’s all about the execution. Trench smart Link below 👇
42
24
3
159
11,506
Now that #GTAVI is almost out, whos waiting for GTA 7? Its going to take at least 15 years so might as well start waiting now.
2
69
OpenAI botched this release. I wish it were the opposite but here we are...
3
62
Finally Sol and Astra 6.2 are available!
Some of you have been asking very politely. Some of you have just been asking. GPT-6.2 Astra and Sol are now available. Super efficient and built to perform where it counts—the real world. openai.com/index/introducing…
1
46
I heard OpenAI uses Opus internally...
2
37
Just got another DGX Spark...help I'm addicted
2
55
A new open-weights DeepSeek V4.1-Flash competitor just appeared. It fits on 2x DGX-Sparks and can ... operate scientific software, check its own work, and FIX its mistakes. It uses the same architecture as GLM-5.3-Flash. This is Sage-S2.1-Flash from Shanghai AI Lab. Here are the model's stats ... 🧠 320B total / 18B active 📚 ~1M token context 👁️ Multimodal 🔓 MIT license 💾 BF16 + FP8 weights downloadable Shanghai AI Lab demonstrated it working with 12,487 mixed medical images. Example application, the model 👉 Identified 139 relevant CT slices 👉 Attempted a reconstruction in 3D Slicer 👉 Detected a slice-ordering inconsistency 👉 Corrected the error 👉 Reconstructed the skeleton in 3D It didn't just describe the images. Also, it operated scientific software and used verification feedback to correct its work. And Sage supports 10+ types of scientific inputs 🧬 DNA / RNA / protein sequences 🧪 Molecular graphs 💎 Crystal structures 📈 Spectra 🧠 EEG / ECG signals Now look at these developer-reported benchies. MLE-bench Lite: 🔥 Sage S2.1 Flash → 90.3 🐋 DeepSeek V4.1 Flash → 89.2 🟠 Claude Opus 5 → 88.0 ⚫ GLM-5.3-Flash → 84.3 🟣 Qwen3.8-Max → 82.2 🟢 GPT-5.6 Sol → 80.7 And compared with GLM-5.3-Flash: OfficeQA Pro 64.7 → 72.2 Harvey LAB 20.0 → 25.0 SpreadsheetBench 2 32.4 → 37.1 Terminal-Bench 2.1 84.3 → 87.9 Not a clean sweep across every benchmark, but these are interesting results for a scientific agent. ⚖️The weights are already here. 💾 BF16 → ~645GB 💾 Official FP8 → ~330GB Raw weight math: 4-bit → ~160GB 3-bit → ~120GB 2-bit → ~80GB Remember all the work Localmaxxers have done getting GLM-5.3-Flash running on affordable hardware? So who's going to quantize it for a 192GB Gorgon Halo? Or two DGX Sparks? 👀 Imagine running your own scientific research agent that doesn't just generate answers. It executes experiments, checks results, and corrects its mistakes. Link in reply
24
34
4
410
43,712
I think ChatGPT delayed their release because they can't compete with Fable
33
Learn languages fast with flash cards and in depth grammar lessons at mell.am
1
47
Codex users, be honest, did you get a Claude sub for Fable?
58
Share here what you built with Fable
38
Rough day for Microsoft Outlook users
463
Still waiting for GPT 6.2 Sol and Astra
1
1
181
Who here is using Google's models? Anyone like Gemini/Carbon?
2
56
Jenseng Huang, was it worth it?
1
64