Can RTX Pro 6000 (Blackwell, 96 GB) run Qwen3.8 Flash-Next?

Last updated: 3 Nov 2026

Probably only partly: the weights are larger than its memory, so part of the model likely ran from system RAM. Measured 271.4 tok/s generation with part of the model offloaded to system RAM (TensorFold Zig, 1 stream, NVIDIA FP4 QAD + MTP; source).

Every measured result for Qwen3.8 Flash-Next on RTX Pro 6000 (Blackwell, 96 GB)

Build	Quant / setup	Engine	tok/s
RTX PRO 6000: Qwen3.8 Flash-Next NVIDIA FP4 QAD on TensorFold Zig, 271.4 tok/s (Mia's AI Lab recipe)	NVIDIA FP4 QAD + MTP	TensorFold Zig, 1 stream	271.4 CPU offload	source

Memory: RTX Pro 6000 (Blackwell, 96 GB) has 96 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 DGX Spark (GB10) · 2x Intel Arc Pro B70 · 2x RTX 5070 Ti · 2x RTX 5080 · 2x RTX PRO 4000 Blackwell · 2x Tesla V100 32GB · 4x RTX 3090 · 6x RTX 3090 · Apple M5 Ultra · DGX Spark (GB10) · RTX 5090 · RTX Spark N1X · Strix Halo (Radeon 8060S)

Other models measured on RTX Pro 6000 (Blackwell, 96 GB): gpt-oss 120B · gpt-oss 20B

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.