Mia (@MiaAI_lab) / X

Mia

6,167 posts

Mia

@MiaAI_lab

Building with AI & LLMs | Insights, recipes, tools & honest experiments

Joined July 2022

Pinned
Mia
@MiaAI_lab
8h
BIG update for DeepSeek v4 Flash 0731 for 2x @NVIDIAAI DGX Sparks ✨ - optional (experimental) vision support - long context decode tok/s increased substantially - improved multi-turn / agent tool calling - optional abliterated weights path - lots of bug fixes Vision support
GitHub - MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark: DeepSeek-v4-Flash 0731 recipe for 2x DGX...
From github.com
Mia
@MiaAI_lab
4m
Run Nemotron 3.5 Lightning on your DGX Spark and RTX 5090/6000 Pro with ease ✨ Snappy model that is great at agentic stuff! Great job @NVIDIAAI 👏 - SGLang - NVFP4 with DSpark - 1M context - 112 tok/s single steam - Up to 362 tok/s at 8 sessions Get it here:
Mia
@MiaAI_lab
44m
I'm impressed with this model and it's so much fun to use. Won't break any records in coding benchmarks, but for agentic tasks it's really capable and lightning fast.
0xSero
@0xSero
1h
DGX Spark & Nemotron-Lightning review & demo. It one shot a pretty valuable media editing task relatively quickly. Happy with this. Better agent, it's meh at coding but all agent tasks went quite well.
00:00
Mia
@MiaAI_lab
1h
Nvidia Nemotron 3.5 Lightning ⚡️ DGX Spark
00:00
Mia
@MiaAI_lab
1h
Nvidia's Nemotron 3.5 Lightning is insanly fast on a DGX Spark, I'm blown away 🤯