@pupposandro: Excited to announce that Lucebox engine now serves Qwen3.8-27B on a single AMD Radeon AI PRO R9700 (32 GB, RDNA4) with …
Summary
The Lucebox engine now supports running the Qwen3.8-27B model on a single AMD Radeon AI PRO R9700 GPU, achieving up to 227 tok/s on code tasks using the DFlash2 drafter with lossless verification.
View Cached Full Text
Cached at: 08/27/26, 05:56 PM
Excited to announce that Lucebox engine now serves Qwen3.8-27B on a single AMD Radeon AI PRO R9700 (32 GB, RDNA4) with the DFlash2 block-diffusion drafter from z-lab:
- up to 227 tok/s on code
- 208 tok/s HumanEval average
- math at 133 tok/s on an off-the-shelf quant that matches an 8-bit reference on HumanEval and GSM8K.
And it is lossless: greedy verification commits only tokens the model itself would produce, so the drafter changes how fast you get the answer, never what the answer is.
Full breakdown in the article below
Similar Articles
You can now run Qwen 3.8 27B on AMD NPUs via FastFlowLM (at a killer 1 tps decode)
AMD's ROCm/FastFlowLM now supports running Qwen 3.8 27B (and other MoE, vision, audio, and embedding models) on Ryzen AI XDNA2 NPUs with no GPU required, offering up to 256k context in a lightweight 17 MB runtime — though decode speed on the 27B model is noted as a sluggish 1 token/s.
@pupposandro: 2.5x faster than llama.cpp on Strix Halo. We just shipped DFlash + PFlash for the AMD Ryzen AI MAX+ 395 iGPU (gfx1151, …
A new toolset (DFlash + PFlash) achieves 2.5x faster inference than llama.cpp on AMD Ryzen AI MAX+ 395 iGPU, demonstrating significant speedups for Qwen3.6-27B with 128 GiB unified memory.
@ItsmeAjayKV: Achievement Unlocked: Running Qwen3.6-27b dense Thanks to the RTX 3090, now I can do this. Running @Alibaba_Qwen Qwen 3…
User benchmarks Qwen3.6-27B on an RTX 3090 using llama.cpp, achieving 35 tok/s generation and 1247 tok/s prompt processing.
@pupposandro: Orders are now open for the new Lucebox Zero 495: https://shop.lucebox.com It’s AMD’s new Ryzen AI MAX+ PRO 495 with up…
Lucebox opens orders for the Zero 495, an AI inference workstation combining AMD's Ryzen AI MAX+ PRO 495 with up to 192GB unified memory and a 32GB Radeon AI PRO R9700, achieving up to 50 tok/s through model splitting across both chips. Starting at $5,999, the preinstalled system ships January 2027 with up to 4TB SSD and optional 100 GbE clustering.
Qwen3.8-Flash-Next turns 4xR9700 into a local AI powerhouse! 120 t/s TG and 12k t/s PP single request with optimized vLLM
The article reports that the Qwen3.8-Flash-Next model achieves 120 tokens/second generation speed and 12k tokens/second prefill on a system with 4x AMD R9700 GPUs using optimized vLLM and a custom Docker image.