LLM Opex

Models

Qwen3.8-2.4T-A95B-FP8: GPU memory and hosting cost

Open weights · 2446.18 billion parameters · Mixture of experts · 262,144-token context · licence other

No cloud sells this model per token: to use it you run it yourself, on GPU instances you rent.

Run it yourself

It needs 3057.7 GB of GPU memory at fp8, the precision it ships in.

CloudCheapest instance that fitsGPUsAn hourA month, around the clock
OCI2 × BM.GPU.MI300X.8, joined by RDMA cluster network8 × MI300X 192 GB in each$96.00$70,080
Nebius3 × gpu-h200-sxm.8gpu-128vcpu-1600gb, joined by InfiniBand8 × H200 141 GB in each$129.60$94,608
AWS5 × p4de.24xlarge, joined by EFA8 × A100 80 GB in each$137.24$100,182
Azure2 × Standard_ND96isr_MI300X_v5, joined by InfiniBand8 × MI300X 192 GB in each$137.28$100,214
Alibaba Cloud4 × ecs.gn8v-8x.16xlarge, joined by eRDMA8 × GPU H 96 GB in each$233.96$170,793
Google Cloud3 × a3-ultragpu-8g, joined by GPUDirect RDMA8 × H200 141 GB in each$254.42$185,727

Several servers: the model is sized across identical servers that hold it together, on instance types whose vendor documents a network between servers; the price is all of them. It is shown where no one server holds the model, or where it costs less than the one that does.

More from Qwen

Similar size, open weights

List prices collected 21 November 2026, refreshed every three hours. No negotiated rates or taxes.