Run DeepSeek-V4.1-Flash (748B) locally with Project Maya on one RTX 5090

Description and use

DeepSeek‑V4.1‑Flash (748 B) runs locally on a single RTX 5090 using Project Maya, achieving ~21 tokens/s with 262 K context after downloading ~350 GB of model files.

Problem

Run the 748B DeepSeek-V4.1-Flash model locally on a single RTX 5090 GPU with limited RAM (128 GB) and NVMe storage.

Outcome

DeepSeek-V4.1-Flash runs locally on one RTX 5090, achieving ~21 tokens/s with 262 K context, after downloading ~350 GB of model files and configuring Maya‑DS4.

Workflow

• Clone Project Maya repository
• Run maya.sh --check to install dependencies
• Run maya.sh --setup with flags: --model DeepSeek-V4.1-Flash-1017 --ds4-quant maya-s --context 262144 --vram-reserve-mib 3072 --no-vision --port 8082 --no-start
• Start the server in a systemd slice without memory limits using systemd-run
• Send a chat completion request via curl to http://127.0.0.1:8082/v1/chat/completions

Evidence

DeepSeek-V4.1-Flash-1017 has 748B parameters. Even Project Maya's own 2-3 bit quant is 340 GB with its Engram tables, and my workstation has 128 GB of RAM.

Source

The first start after setup also runs Maya's speed calibration (below) and took about four minutes here; a normal start took 20 seconds.

Source

The flags that matter: --model DeepSeek-V4.1-Flash-1017 --ds4-quant maya-s picks the model and the smallest quant.

Source