DeepSeek V4.1 Flash Runs at 20 tokens/s on a Single 3090, 2x Possible with More RAM
casper_hansen_ · x · 2026-11-12
Developer casperhansen reports running DeepSeek V4.1 Flash locally at 20 tokens/s on a single RTX 3090 plus 64GB RAM with "zero quality sacrificed." The stack uses a vLLM frontend for scheduling, tool calling, and OpenAI/Anthropic-compatible APIs, with ExLlamaV3 handling the forward pass; he plans to replace it with his own implementation. He estimates adding another 64GB of RAM would roughly double throughput.
Related event: DeepSeek V4.1 Flash Runs at 20 tok/s on a Single RTX 3090(2 posts)→
More from Infra
- Budget GPU server rental tips: OVH KS-6/7, FiberState, and asking for unlisted stock — realmrfakename · 2026-11-12
- AMD EPYC review image looks uncannily like logit artifacts from ViT segmentation models — giffmana · 2026-11-12
- llama-modchip runs 284B DeepSeek-V4-Flash IQ1 on a pure 64GB CPU with zero GPUs — pmttyji · 2026-11-12
- Agent Substrate Calculator Estimates Session Resume Speed Under Load — pjausovec · 2026-11-12
- Dell expands AI Data Platform: agents have a data-context problem, not a model problem — DavidLinthicum · 2026-11-12
- SGLang Megakernel Pushes Muse Spark to 1,109 tok/s, 2.1x Over Baseline — hsu_byron · 2026-11-12