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.
VR retweeted
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
VR retweeted
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
VR retweeted
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…
VR retweeted
Portfolio Site up
realdealcpa.ai/
VR retweeted
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 !
VR retweeted
When you run out of @AnthropicAI tokens on a max plan and know 5 more minutes until the next window 🤣













