unbug

@unbug

Local LLM V100 96G & enjoy Omarchy; Tday unbug.github.io/tday/ ; CODELF (Github star 14k); MIHTool (Mentioned in Google I/O'13)

Los Angeles, CA

Pinned
unbug
@unbug
Oct 2
Just a bit of insight: people are eager to build their own rigs for local LLMs, the same way we were obsessed with building gaming PCs 30 years ago. x.com/i/chat/group_j…
1
unbug
@unbug
3h
Turns out you can tune Strata for more prefill speed. On Qwen3.8-Flash Q6-KXL setup: +72% prefill on short context, +27% on long context, and VRAM hit rate stays pinned at 100%. The main knobs are --pcie-frac, layer_split, and --trim-stage-weights. The catch: MTP still isn’t
3
unbug
@unbug
3h
The ticket to Muse locally is a Mac Studio.
Unsloth AI
@UnslothAI
3h
Meta releases Muse Spark Open, a new SOTA open model. Run on a Mac Studio via Dynamic 2-bit Unsloth GGUFs. Muse-Spark-Open-816B-A42B supports text, images, video and audio input with 1M context. GGUF: huggingface.co/unsloth/Muse-S… Guide: unsloth.ai/docs/models/mu…
1
unbug
@unbug
4h
New models come, new models go. In the end, we all just run Qwen locally. That’s the story of 2026 open-weight models. Why?
7
unbug
@unbug
5h
Nemotron is super fast on NVIDIA GPUs—faster than any other model, even without MTP/DFlash. But… but… but…
Unsloth AI
@UnslothAI
6h
NVIDIA releases 2 new models: Nemotron-3.5-Bolt and Nemotron-3.5-Super-VL. Nemotron-3.5-Bolt-74B-A9B runs on 24GB RAM. It delivers top-tier performance for its size. Super-VL-120B-A12B runs on 82GB RAM. Bolt GGUF: huggingface.co/unsloth/NVIDIA… Guide: unsloth.ai/docs/models/ne… Super
1