ToolBraid🪢 (@ToolBraidComp) header
ToolBraid🪢 (@ToolBraidComp) profile picture

Building things I’m technically not qualified to build. Solo, self-funded. Creator of ToolBraid. ☕ https://teapawt.org/t.co/Ifs4bHrILQ

Joined August 2021
Unreleased beta engine at 128K context. A single RTX 5090. 🚀 I've pushed Qwen 27B NVFP4 on #TensorFold to previous 309 to 326.93 tokens/ in a real cold-decode test. Part that matters most: 2,048 generated tokens. Byte-for-byte identical output. Zero output drift.
1
1
1
166
Replying to @thsottiaux
Without usage. Not able to test it until Friday when usage refills
22
~344 tokens/sec average decode. ONE RTX 5090. 26 minutes of local AI coding in Claude Code. THREE automatic context compactions. Qwen3.8 27b NVFP4 - The agent kept working. 🔥 Experimental Unreleased BLACKFURY Exact on #TensorFold Setup + independent test results below 🧵
3
2
1
10
862
BLACKFURY Exact V1.0.1 Released - built on #TensorFold by @ashxhart 🚀 Qwen3.8-27B NVFP4 on one RTX 5090: 309.53 tok/s decode at 131K context in a single stream +10.20% vs the previous release, comparing medians from separate runs. Code 👇
4
2
18
5,605
Qwen3.8-27B NVFP4 + DFlash2 running locally on a single RTX 5090 - powered by #TensorFold 🔥 ⚡ 753.3 tok/s peak live 📊 376.5 tok/s average decode across 36 requests 🧠 Thinking LOW 🛠️ Real coding, browser checks and visual fixes Peak at 5:21 - even Goku powers up 😂
100
734 tok/s coding peak on ONE RTX 5090 🔥 330 tok/s average decode in the same loop. BLACKFURY Exact: my #TensorFold variant optimized for single stream. Qwen3.8-27B NVFP4 + DFlash2. 128K window. Peak sampled over ~1s. Built on @ashxhart's work. Code + results below 🧵
4
1
10
3,570
RTX 5090. 12 branches. Over 1,000 tok/s🤯 Qwen3.8-27B NVFP4 locally on my experimental TensorFold/OMP. 🚀 1,081 tok/s peak aggregate ⚡ 791 tok/s average across the generation batch 🧠 Thinking ON, LOW effort 💾 64K-context Local AI is getting wild @ashxhart and #TensorFold 🔥
10
5
4
46
8,753
One RTX 5090. Qwen3.8-27B NVFP4. Eight synchronized branches sharing one context. With thinking set to low, I measured 499 tokens/s aggregate, including reasoning, with a 716.3 tokens/s peak over a roughly one-second window, with 66k context In this run, the agent generated eight Three.js components, integrated them and passed the browser checks in 101 seconds. Running locally with #TensorFold + #OMP. Live coding and the result below 👇
1
2
112