Claude Code · Anthropic · OpenAI · Nvidia · Claude · Codex · GitHub
Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
English · 简体中文 · 日本語 · Deutsch · Français · Español · Português.
Key facts
- A card with more VRAM is faster: an RTX 3090 (24 GB) should write about 100-140 tokens per second
- A voxel pagoda garden, 1 shot prompt running on an RTX 5070 with Strata (IQ3_S, 128K context)
- full video (49 s)
- NVIDIA: Q2_0 with engine 0.1.36, the other rows with 0.1.26 (4K answers, 32K prompts)
- Strata loads 35-55 GB into your RAM and locks part of it for the graphics card
Summary
Run a 125-billion-parameter AI model on your own gaming PC NVIDIA or AMD graphics card (12 GB or more) · Windows or Linux · free and open source. A voxel pagoda garden, 1 shot prompt running on an RTX 5070 with Strata (IQ3_S, 128K context) · full video (49 s) Strata runs Qwen3.8-Flash-Next on a normal PC. Writes answers: how fast the reply appears in a short chat. 60 tokens per second is faster than you can read.