Strata open-source engine runs 125B-parameter Qwen3.8-Flash-Next on consumer gaming PCs
Strata, an open-source inference engine built by a single developer, runs the 125B-parameter Qwen3.8-Flash-Next locally on ordinary gaming PCs, earning 5000+ GitHub stars in 8 days (later posts show 5.7k). Independent tests by security researchers and users across hardware tiers confirm its feasibility and throughput, with entry barriers far lower than expected.
Confirmed
- Strata offers one-click Windows/Linux installation, runs the 125B model on consumer hardware, and exposes local OpenAI/Anthropic-compatible APIs that plug directly into Claude Code (@alexverem)
- Its core mechanism splits work across GPU and CPU with tiered storage rather than holding the whole model in VRAM, enabling 125B-class MoE models on a 12GB RTX 5070, with reported speeds up to 93 tokens/s (@udmrzn, repost)
- Security researcher evilsocket demonstrated running an IQ1M aggressively quantized qwen3.8-flash-next-coder on a 16GB NVIDIA GPU, estimating the entry bar at a 12-24GB VRAM card (@evilsocket)
- Japanese user CurieuxExplorer measured the 87GB Qwen3.8 Flash Next at 120-150 t/s on a single RTX 5090 with 4K t/s prefill, integrated with LibreChat and a WebUI (@CurieuxExplorer)
- A repost claims even an old cheap DDR3 machine can run the 125B model at 70 t/s (@udmrzn, repost)
Why it matters
- Local deployment of large models usually requires servers or multi-GPU clusters; Strata pushes the bar down to 12-16GB VRAM or even DDR3-era PCs, valuable for privacy-sensitive and offline workflows
- OpenAI/Anthropic-compatible APIs let existing toolchains like Claude Code and LibreChat switch to local models at near-zero cost
- Independent tests spanning different hardware tiers validate real-world usability and throughput beyond marketing figures
2026-10-01 ~ 2026-10-03 · 7 related posts
- Episode 1: Strata open-source engine runs 125B-parameter Qwen3.8-Flash-Next on consumer gaming PCs(2026-10-01, 7 posts)
- Episode 2: Strata Lets Consumer PCs Run 180B Models Locally(2026-10-02, 3 posts)
- Episode 3: RTX 5070 12GB Runs 177B Model Locally at 11-15 tok/s(2026-10-03, 2 posts)
- Episode 4: Strata runs 125B-parameter Qwen model on 12GB GPUs(2026-10-03, 2 posts)
Primary sources
- [source] 87GB Qwen3.8 Flash Next runs at 120-150 t/s on a single RTX 5090 — CurieuxExplorer · 2026-10-01
- [source] Running quantized Qwen3.8 coder on a 16GB GPU with Strata — evilsocket · 2026-10-01
- Strata runs 125B Qwen3.8-Flash-Next on a 16GB consumer GPU — evilsocket · 2026-10-01
- [source] Strata open-source engine runs 125B Qwen3.8-Flash-Next on gaming PCs, 5k stars in 8 days — alex_verem · 2026-10-02
- Strata repo: 125B Qwen3.8-Flash-Next on consumer hardware with local OpenAI/Anthropic APIs — alex_verem · 2026-10-02
- Strata runs a 125B model at 70tps on old DDR3 PCs with a cheap GPU — udmrzn · 2026-10-03
- Open-source Strata runs 125B MoE models on 12GB VRAM at up to 93 tokens/s — udmrzn · 2026-10-03