AI-Powered Coding with Qwen3.8-Flash-Next
High-performance AI experiments on NVIDIA GB300 NVL72
1Technical Specifications of Qwen3.8-Flash-Next
Qwen3.8-Flash-Next is a 125-billion parameter multimodal mixture-of-experts (MoE) model. It activates 6 billion parameters per token and features a native 262,144-token context window, expandable to 1 million tokens with YaRN. The model uses a hybrid architecture combining Gated DeltaNet (GDN) and Qwen Sparse Attention (QSA), optimized for large-context applications.
2Advantages of Hybrid Architecture
Three out of four layers use GDN to compress historical context into a fixed-size recurrent state, eliminating KV cache growth as sequences lengthen. The remaining layer employs QSA for precise retrieval across full context. QSA aggregates sequences into micro-blocks, estimates their importance at block level, and selects only the most relevant regions.
3Performance Improvements
Alibaba benchmarks show QSA improves efficiency for 1M-token workloads. Compared to full attention, it delivers up to 7.6x speedup during prefill and 4.9x during decoding. At 1M-token context length with 90% prefix-cache hit rate, Qwen3.8-Flash-Next achieves 8.6x the prefill throughput of Qwen3.7-Plus.
4Running on NVIDIA GB300 NVL72
The NVIDIA GB300 NVL72 features a rack-scale architecture integrating 72 Blackwell Ultra GPUs. Its large 130 TB/s NVLink domain eliminates bottlenecks from traditional networks. On this platform, Qwen3.8-Flash-Next processes over 16,000 tokens per second per GPU.
5Local Hardware Support
The model also runs on local NVIDIA hardware including DGX Station, DGX Spark clusters, and workstations with four RTX PRO 6000 Blackwell Max-Q GPUs. Developers can prototype on local hardware and scale the same model to GB300 NVL72 for production.
6Fine-tuning and Learning Options
NVIDIA NeMo AutoModel offers PyTorch-native fine-tuning with Day-0 Hugging Face checkpoint support. Options include full SFT or memory-efficient LoRA fine-tuning. Reinforcement learning is available through NVIDIA NeMo RL recipes.
7Inference Engine Options
NVIDIA supports multiple inference stacks for diverse developer needs. SGLang, vLLM, and TokenSpeed provide open-source inference recipes for greater performance control on NVIDIA-accelerated platforms.
8The Future of AI-Powered Coding
Qwen3.8-Flash-Next's large context window and hybrid architecture usher in a new era for AI-assisted coding. Its high throughput and low latency on platforms like NVIDIA GB300 NVL72 hold revolutionary potential for complex software development processes.
Original article: Nvidia Developer Blog — Qwen3.8-Flash-Next ile Yapay Zeka Destekli Kodlama