A 12GB RTX 5070 is running Qwen3.8-Flash-Next at a reported 141 tps.
This is a AI post classified by AGK Intelligence as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
A 12GB RTX 5070 is running Qwen3.8-Flash-Next at a reported 141 tps. A Localmaxxer posted benchmarks using Strata 0.2.10 with expert caching, CPU/RAM offloading, and speculative decoding. The hardware stats 🟢 RTX 5070 12GB 🧠 Intel i7-12700K 💾 64GB DDR4 💽 NVMe SSD 🐧 Ubuntu + CUDA 13 The model is ... 🧠 Qwen3.8-Flash-Next 📦 IQ3_XXS quantization 📚 192K context configured ⚙️ Strata inference engine And the results are ... ⚡ 141.3 tps → 9-prompt aggregate decode rate ⚡ 118.7 tps → short-chat median 📥 2,236 tps → 4K fresh prefill 📥 2,729 tps → 16K fresh prefill The model uses a Mixture-of-Expert
Posted by David Hendrickson (12.8k followers) 1 days ago · 34 likes · 2.9k views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- Qwen 4 is in my hands and I can't stop grinning 🔥 — @aijoey
- Qwen 4 (unnamed quant) — @loktar00
- 北冥有鱼，其名为鲲。 — @NFT_Chen
- If you want to get started with Local AI but dunno where to start, THIS IS FOR YOU 🚨 — @javierbits
- 💥重磅！Qwen3.8-Flash-Next 量化版炸裂升级：Token消耗直接腰斩50%，准确率暴涨15%！本地32GB丝滑跑通125B级MoE！ — @NFT_Chen
- This could be so cool. — @niklaslenz_ai
- Qwen is teasing a new model — @RoundtableSpace
- 时代变了，以前是token每秒，有人提出了秒每token。。。。 — @mylifcc
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.5k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:50 UTC. Full method.