Model facet · Hardware

Qwen3.8-2.4T-A95B GPU Requirements: 2,996 GB at FP8

Qwen3.8-2.4T-A95B is a 2.4T-parameter MoE with 95B active per token. FP8 weights: 2.96 TB. BF16 weights: 5.87 TB. Not a single-node model. NVIDIA Dynamo's production recipe uses 16× GB300 across 4 nodes at TP16 with FP8 weights and FP8 KV cache.

VRAM by precision

Source: vLLM recipe, 8 September 2026. Bytes-per-parameter is multiplied by 2.4T total parameters (95B active per token). Numbers are the parameter-only weight footprint before KV cache, activations, or runtime overhead.

PrecisionWeightsSizedB300 (268 GB)MI355X (288 GB)H200 (141 GB)GB300 tray
BF164.45 TiB5,871 GB24 GPUs24 GPUs48 GPUs6 trays
FP82.27 TiB2,996 GB16 GPUs16 GPUs32 GPUs4 trays (TP16)

NVIDIA Dynamo production recipe

NVIDIA Dynamo's reference serving topology for this model: 16× GB300 across 4 nodes, TP16 over MNNVL, FP8 weights and FP8 KV cache. Confirms the vLLM FP8 estimate and is the configuration to benchmark against if you are self-hosting.

How these figures are calculated

Bytes-per-parameter is applied to 2.4T total parameters (95B active per token). Numbers are the parameter-only weight footprint before KV cache, activations, or runtime overhead. Multiply by ~1.2 to budget for sustained inference at the 262K native context, and by ~1.4 if you intend to extend to the 1,010,000-token extended context.

Quantized variants and derivative releases

RadixArk's NVFP4 quantization is already published on Hugging Face — derivative release date 7 August 2026, ahead of the official weights. NVFP4 brings the FP8 footprint down further; check the derivative listing for the actual weight size and any quality caveats before deploying.

Ready to test the workflow?

Create account & add credits

Weights are publicly available

Qwen3.8-2.4T-A95B weights are released under the qwen3.8-max license and can be pulled from the Hugging Face repository linked in Sources. Confirm the license tag and any use restrictions against the official repository before self-hosting at scale.

Architecture

2.4T-parameter Mixture-of-Experts (95B active per token), native 262,144-token context, extensible to 1,010,000 tokens via YaRN. Text-only input on this checkpoint.

Frequently asked questions

What GPU do I need to run Qwen3.8-2.4T-A95B?

At FP8: 16× B300 (268 GB each), 16× MI355X (288 GB each), or 32× H200 (141 GB each). At BF16: 24× B300, 24× MI355X, or 48× H200. NVIDIA Dynamo's production recipe runs 16× GB300 across 4 nodes at TP16 with FP8 weights and FP8 KV cache.

Can Qwen3.8-2.4T-A95B run on 16GB VRAM?

No. The FP8 weights alone are 2.96 TB. Even a heavily quantized INT4 build sits well above what consumer 16 GB cards can hold, and the 95B-active MoE routing makes any single-GPU serving impractical regardless.

How is VRAM estimated?

Bytes-per-parameter is multiplied by 2.4T total parameters (95B active per token). The figures are the parameter-only weight footprint before KV cache, activations, or runtime overhead — multiply by ~1.2 for sustained 262K-context inference and ~1.4 for the 1M extended context.

Where is the live Qwen3.8-2.4T-A95B model page?

The canonical model page with current OneInfer pricing, capabilities, and availability is /models/Qwen/Qwen3.8-2.4T-A95B. This page is a focused facet of that entity, not a replacement for it.

How should I treat benchmark or price claims?

Check each claim's provenance label and observed date. Vendor-reported and independently verified numbers are shown as separate evidence classes on this hub.

Is Qwen3.8-2.4T-A95B open source?

Yes — weights are released under the qwen3.8-max license. Confirm the license tag against the official Hugging Face repository before self-hosting at scale.

Put Qwen3.8-2.4T-A95B to work

Fund a controlled evaluation, start with a prepared prompt, and measure quality and cost on your own workload.