VR (@RealDealCPA) header
VR (@RealDealCPA) profile picture

Business | Finance | Tech | Ai | Debate | Opinions are my own | Always have fun ! | Connect with good people! | Work hard | Follow to get ahead !!

United States
Joined August 2023
Photo by VR (@RealDealCPA)Photo by VR (@RealDealCPA)Photo by VR (@RealDealCPA)Photo by VR (@RealDealCPA)Photo by VR (@RealDealCPA)Photo by VR (@RealDealCPA)Photo by VR (@RealDealCPA)Photo by VR (@RealDealCPA)Photo by VR (@RealDealCPA)Photo by VR (@RealDealCPA)
IJ ! Give it a try!
2
3
1
5
200
Running GLM-5.3-Flash on 2× DGX Spark with NVIDIA Flare ✨ - 1M context window, 2.32M-token shared KV pool - Prose decode, single stream: 117.2 tok/s - Prose decode, 2 concurrent: 167.4 tok/s aggregate - Prose decode, 4 concurrent: 215.8 tok/s aggregate - 32K prefill: 2,327.9 tok/s - Available memory after loading: ~13 GiB on head /worker each Checkpoint: GLM-5.3-Flash-NVFP4-MXFP8-CSF-QAD github.com/NVIDIA/flare-loca…
NVIDIA just released Flare, a local inference server built for DGX Spark and RTX Blackwell GPUs - Built for long chats, agents and tool calls - Serves from Rust, no Python - Plans memory up front - FP8 KV cache by default Interesting timing... right around when DeepSeek open-sourced their inference engine. Link below.
66
28
18
267
43,587
Are you paying for bookkeeping software? Introducing IRON BOOKS Built to be the best in the business and its free (for now) No cert
🤖 Made with AI
1
2
7
186
iJ is all you need Free and does it all, choose any model and get after it Code, office work, creative Did I mention free ? Or you could just keep all your stuff on someone else’s computer Same same
1
3
3
133
You can now train your own Decision model with our free notebook! 💡 Qwen3.5-4B will generate decisions instead of text on just 8GB VRAM locally. Learn to data prep (state, questions, gold answers), train, serve. Notebook: colab.research.google.com/gi… Guide: unsloth.ai/docs/basics/train…
You can now train your own Decision model like Jev locally! We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM. Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo. We fine-tuned with a Clef head using Unsloth and LoRA (r=64) for one epoch, increasing downstream accuracy from 30–37% to 78%. GitHub: github.com/unslothai/unsloth Guide and Notebooks: unsloth.ai/docs/basics/train…
112
450
67
3,736
355,030
Iron Jarvis !
2
1
5
338
Iron-Jarvis
🤖 Made with AI
1
3
5
360
Seize the day
2
2
22
542
VR retweeted
Check out the latest Iron Jarvis commercial ! Model: Seedance 2.5 (only available on maker mode) Thanks @tsi_org @pixio_ai Repo in the comments 🔥
1
3
2
9
434
VR retweeted
Iron Jarvis got featured ! youtu.be/HQqX4rF1nDM?is=3v2Z…
4
1
1
9
475
IRON JARVIS DEMO : Desktop app - control all your agents, subscriptions, local models, files, media - All in one place ! My best build so far and still working !
6
2
10
450
VR retweeted
On the run !
🤖 Made with AI
3
2
11
386
VR retweeted
Happy Independence Day ! America 🇺🇸🏈🏈🇺🇸 Title: American-Engine ! Made with @pixio_ai and @claudeai
2
1
6
112
VR retweeted
CPAs can be creative check out my latest Title: Lightning Lasso Cred: VR using @pixio_ai @claudeai
6
2
2
21
892
Trying to get my last bit of Fable 5 only land right back to Opus 4.8 @tsi_org / @pixio_ai
1
2
10
465
When you run out of @AnthropicAI tokens on a max plan and know 5 more minutes until the next window 🤣
3
2
6
426