community-verified · measured pool data

Can the RTX 3090 24GB ×4 run DeepSeek-V4-Flash-0731-GGUF?

Yes — community-measured at 41 tok/s (2 runs at 2-bit).

Verified single-stream runs on the RTX 3090 24GB ×4 from the localmaxxing public pool. Every number on this page is measured — nothing here is estimated.

Quantization	Median tok/s	TTFT (ms)	Peak VRAM	Max context tested	Engines
2-bit	41	18774	90.3 GB	131,072	llama.cpp

Go deeper

I have a goal — find models that fit my use case → I have hardware — browse everything my rig can run → All machine × model answer pages →