Can 6x RTX 3090 run Qwen3.8 Flash-Next?

Probably only partly: the weights are larger than its memory, so part of the model likely ran from system RAM. Measured 45.9 tok/s generation with part of the model offloaded to system RAM (llama.cpp-multigpu fork 134489582, layer split, UD-Q4_K_XL (~111.3 GB), q8_0 KV; source).

Every measured result for Qwen3.8 Flash-Next on 6x RTX 3090

Build	Quant / setup	Engine	tok/s
6x RTX 3090 on a Ryzen 9 7950X (4 on USB4 eGPU docks): Qwen3.8 Flash-Next at 45.9 tok/s	UD-Q4_K_XL (~111.3 GB), q8_0 KV	llama.cpp-multigpu fork 134489582, layer split	45.9 CPU offload	source
6x RTX 3090 on a Ryzen 9 7950X (4 on USB4 eGPU docks): Qwen3.8 Flash-Next at 45.9 tok/s	UD-Q4_K_XL (~111.3 GB), q8_0 KV	llama.cpp upstream df03399b8, layer split	38.5 CPU offload	source

Memory: 6x RTX 3090 has 144 GB. Qwen3.8 Flash-Next weights are about 110.1 GB at Q4_K_M (180B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.

Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.

All measured speeds for Qwen3.8 Flash-Next: best home rig for Qwen3.8 Flash-Next.

Qwen3.8 Flash-Next on other hardware: 2x Intel Arc Pro B70 · 2x RTX 5070 Ti · 2x RTX 5080 · 2x RTX PRO 4000 Blackwell · 2x Tesla V100 32GB · DGX Spark (GB10) · RTX 5090

Not enough VRAM? Rent before you buy. Run Qwen3.8 Flash-Next on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.