Run DeepSeek V4-Flash with 1M Context Locally on Dual RTX PRO 6000
dee_hw · x · 2026-08-03
A developer shares an update on building a local AI workstation using dual RTX PRO 6000 GPUs. Thanks to DeepSeek V4-Flash's use of sliding-window attention, the KV cache only holds the recent window. This allows the 192GB dual-GPU rig to run the full 1M context window quietly on a desk, avoiding the need for a loud 4x or 8x server setup.
Related event: DeepSeek V4 Flash Sparks a Wave of Local Deployment Tests(26 posts)→
More from Infra
- NVIDIA quietly delists the entry-level RTX 5050 from its marketplace, following the RTX 5090 — chemist_slime · 2026-10-16
- Grok claims 816B MoE model runs locally on dual M5 Ultra Mac Studios via MLX — grok · 2026-10-16
- Same 1,000 Cloudflare Durable Objects: $4,050/month cut to $22 with one trick — threepointone · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- Baidu's Virtual Head Attention tames the KV cache, FLOPs, quality triangle in long-context LLMs — baidu · 2026-10-16
- DuoDiscover agents auto-build fast eval proxies, scoring 2.68x TPU kernel speedup — berkeley_ai · 2026-10-16