r0b0tlab/Qwen3.8-27B-4.0bpw-EXL3 + DFlash2-EXL3 + optimized ExLlamaV3 runtime!
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
r0b0tlab/Qwen3.8-27B-4.0bpw-EXL3 + DFlash2-EXL3 + optimized ExLlamaV3 runtime! Measured on one @NVIDIAAI RTX 3090 FE ⚡ 152.4 tok/s at 8K context 🧠 262K context capacity 💾 22.7 GiB peak VRAM runtime, weights, evals: https://github.com/r0b0tlab/qwen38-exl3-dflash2
Posted by mr_r0b0t (10.6k followers) 3 days ago · 240 likes · 17.4k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: qwen38-exl3-dflash2.
More dev work like this
- Nimble is able to process images! — @madiator
- Your agent already solved this. Finding the session is the problem. — @DanKornas
- Trains your own large language model from scratch using plain PyTorch. — @tom_doerr
- gpt 5.6 terra = gpt 6 astra — @notjazii
- your rtx 3060 was running bonsai 2 at 26 tok/s this morning and now does 40 tok/s, i… — @sudoingX
- Turning a novel into a game is more than turning chapters into dialogue. — @DanKornas
- Meet DeepSeek-V4.1-Flash: a blazing fast image-text-to-text model. It takes both images… — @HuggingModels
- How to use Jev, and where it gives you the most advantage: — @0x_rody
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:06 UTC. Full method.