ToolBraid Companion is live on the Microsoft Store 💪🏻
apps.microsoft.com/detail/9P…
Built for developers. Browser tools + WebMCP on supported sites, straight from your Codex session.
Free. You choose which sites your AI can access.
Who’s up for trying it? 👀
3
353
Replying to @Night_Diver2543 @ashxhart
My guy, that's a demo on 2.8k - 4.7k tok... A demo has no utility in real world use case. Go with 128k context and get back to me with real work demo 👀
1
34
Replying to @Yves_From_BE @ashxhart
I'm sure that in the future Ash can push it to 300tps
It's so much room to optimise our local hardware that ee haven't explored yet
76
Replying to @snow_el
Call me when they get to 310tps in context 128k.
Demos are worthless without an use case.
3
575
Replying to @ashxhart
And it's still room for improvement💪🏻 pushing forward local AI.
More updates soon
80
Replying to @ToolBraidComp @ashxhart
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 👇
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 😂
74
Replying to @ashxhart
I didn't had the time to get that far in testing 😂 i haven't tried sub agents😅 i was to excited about the results🤣
1
148
Qwen 4 27b it's around the corner 🔥
Can't wait to play with it.
Exciting news for #LocalAI
📢 Meet Qwen4-Max, your new AI teammate for work, creativity, and discovery!
Qwen4-Max is built on a new MoE architecture with native vision and a 1M-token context window.
Highlights:
- Outperforms Qwen3.8-Max with up to ~50% fewer tokens, while average cost per task drops over 60% in our internal evaluation.
- Advances real-world productivity through greater proficiency with professional tools, stronger long-horizon execution, and higher-quality deliverables.
- Handles real tasks, including 3D modeling, game development, manufacturing, finance, law, healthcare, and frontier scientific discovery.
- $1.5/M tokens for input, $4.5/M tokens for output, and $0.075/M tokens for implicit caching — all lower than Qwen3.8-Max, with implicit caching down by 70%.
The API is live on QwenCloud. You can also try Qwen4-Max on Qwen Studio, QwenWork and Qoder.
Start building today! 🚀
- Blog: qwen.ai/blog?id=qwen4-max
- API: qwencloud.com/models/qwen4-m…
- Token Plan: qwencloud.com/pricing/token-…
More to come! The open weights of smaller Qwen4 models will be released. Stay tuned. 👀
1
86
Replying to @noprejudices101 @ashxhart
Cold prefill: 129,024 tokens in 50.44s (~2,558 tok/s), model already loaded. Near the limit in the filmed loop: 117,632 cached + 9,719 new tokens, 4.99s prefill (~1,947 new tok/s), 5.01s to first token.
1
71
Source, patches, setup and measurements:
github.com/Maharajahu/qwen-p…
One 32 GB GPU, with active inference entirely in VRAM.
If you try it on your 5090, I'd love to see your results. #LocalAI
3
212
Parallel still works: 12 synchronized branches, thinking OFF.
790.23 tok/s across the generation batch.
1,079.12 tok/s sampled aggregate peak.
Different workload and context from the single-stream test. These are combined rates across all 12 branches.
1
171
In that coding loop:
330.37 tok/s weighted decode average
734.17 tok/s sampled 1-second peak
The average excludes prefill and tools. Whole-file updates repeat existing code, so the peak isn't a promise for arbitrary code generation.
1
160
Controlled test: 129,024 input + 2,048 output tokens, thinking LOW.
280.88 tok/s warm decode median, 281.19 best request.
+4.58% vs my preserved original engine.
Tokens, text and reasoning matched the original across 37 recorded comparisons.
207
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 🧵
Replying to @ItsmeAjayKV @NolmerPortion
Good luck to us to secure any of these GPUs... Are expensive as fk now...
1
137




