Qwen3.8-Flash-Next: 180B total / 6B active, runs on consumer GPUs via Strata offloading
drdanielbender · x · 2026-11-13
Tier two of the author's model recommendations:
- Qwen3.8-Flash-Next: scores 29 on the intelligence index with 180B total / 6B active parameters. With the right quantization and offloading setup via Strata (@coldniko), it runs on consumer gaming GPUs with 64GB+ RAM, or on 128GB shared-memory machines like DGX Spark and Strix Halo.
Key practical takeaway: low active-parameter MoE plus offloading tools brings a 180B-class model within reach of home hardware.
Related event: Open-Weight Model Tiers: Kimi K3.1 Pro Leads at 46, Budget Picks for APIs(2 posts)→
More from Infra
- 'Maybe the Great Filter Is Permitting a 10GW Data Center' Quip Resonates — Dr_Singularity · 2026-11-13
- Fab capacity jumps to 1.117M 8-inch-equivalent wafers/month, 78.9% on 12-inch — teortaxesTex · 2026-11-13
- Microsoft and Claude go down simultaneously, taking apps offline with them — ThePeterMick · 2026-11-13
- llama.cpp ships v1.0.0, the landmark first stable release for local LLM inference — TheApadayo · 2026-11-13
- Singapore files 41 charges against man in alleged Nvidia AI chip smuggling scheme to Malaysia — Polymarket · 2026-11-13
- Meme: All modern digital infrastructure rests on one tiny Model Hub pillar — pcuenq · 2026-11-13