Skip to content

Instantly share code, notes, and snippets.

View yume-arasaki's full-sized avatar

Yume_Arasaki yume-arasaki

View GitHub Profile
@yume-arasaki
yume-arasaki / gist:01134e3671c61d9ed7f4620ed0c21cd1
Created August 20, 2026 22:57
AI Cookshow Epsiode 1 : Dual Models, Two Sparks, Qwen 3.8 27B Dense * Orinth MOE
# Two DGX Spark recipes: Qwen 3.8 27B (SGLang + DSpark) + Ornith-1.5 35B-A3B (vLLM + MTP)
Verified on 2x DGX Spark (128GB unified each). Both serve OpenAI-compatible endpoints.
Recipes: r0b0tlab/qwen38-27b-nvfp4-sm121-sglang · MiaAI-Lab/Ornith-1.5-35B-A3B-DGX-Spark
## Spark 1 — Qwen 3.8 27B dense, NVFP4, SGLang with DSpark speculative decoding
Weights: main model at `/model`, DSpark draft at `/draft` (in-container mounts).
```bash
@yume-arasaki
yume-arasaki / gist:e24bf2614ee0419c86250cee6ad7ce01
Created August 7, 2026 19:02
MiniMax H3 Hardware Map — Sources and Recipes (8th of August 2026)
Every number in the H3 hardware landscape map, traced to its source.
Consumer GPU benchmarks
- kingy.ai H3 hardware review and guide (3060/4070/4090/5090 data, SGLang topology comparison)
kingy.ai/ai/ai-guides/minimax-h3-local-installation-hardware-guide/
- ai-muninn.com RTX 5090 NVFP4 benchmark (coolthor pack, 175s measured)
- xhinker Medium 5090 field report (~2.5 min T2V, ~7 min I2V, Blackwell INT8 vs FP8)
- HuggingFace Comfy-Org/MiniMax-H3 discussion threads #3, #6, #11, #18, #26
huggingface.co/Comfy-Org/MiniMax-H3/discussions