Text generation · served with vLLM · ↓ 12.7K downloads a month · View on Hugging Face
intel-ai/Qwen3.8-Flash-Next-MXFP4-BF16Attn-PLEMXFP8-CT-AutoRound needs about 150.9 GB of GPU memory for conversations of up to 8,192 tokens. It runs on 8x RTX 3090 from $1.57/h right now; best value: 4x RTX PRO 5000 at $2.73/h.
Weights
133 GB
GPU memory needed
about 150.9 GB
Conversation length
8,192 tokens
Model allows
262,144 tokens
Memory · disk
74.5 GB · 187 GB
Architecture
Qwen4ExpForConditionalGeneration
Licence
other
Versions of Qwen3.8-Flash-Next ~180B
The same model packaged differently: a quantized version needs less GPU memory and runs on a cheaper machine.
Name and access:Qwen3.8-Flash-Next-MXFP4-BF16Attn-PLEMXFP8-CT-AutoRound · with a key
$2.73/h from your balance while it runs, billed by the hour; stop it from its page. GridPup rents the machine, which downloads the model from Hugging Face (usually ready in 10 to 15 minutes), and gives you an https address, keys and a Playground.
Questions
How much GPU memory does Qwen3.8-Flash-Next-MXFP4-BF16Attn-PLEMXFP8-CT-AutoRound need?
About 150.9 GB for conversations of up to 8,192 tokens: 133 GB of weights, the cache for one full-length conversation and the runtime's own memory.
What is the cheapest GPU to run Qwen3.8-Flash-Next-MXFP4-BF16Attn-PLEMXFP8-CT-AutoRound?
Right now 8x RTX 3090 at $1.57 an hour; 4x RTX PRO 5000 at $2.73 an hour is the best value for its speed. Prices are live offers from GPU clouds, checked every 15 minutes.
Can Qwen3.8-Flash-Next-MXFP4-BF16Attn-PLEMXFP8-CT-AutoRound run on an RTX 4090?
Not on one: it needs about 150.9 GB and an RTX 4090 has 24 GB. Use a bigger GPU, or a smaller (quantized) version of the model.
How do I deploy Qwen3.8-Flash-Next-MXFP4-BF16Attn-PLEMXFP8-CT-AutoRound as an API?
Pick a machine on its GridPup page and press Deploy: GridPup rents the GPU, downloads the model from Hugging Face and serves it at an https address with keys and OpenAI's chat API, billed by the hour.
Prices are per hour for the whole machine and its disk, right now. Speed is Vast's DLPerf score of the machine, relative to the cheapest. Best value: the most speed per dollar. Only machines with a Vast reliability of 90% or more that download at 200 Mbit/s or more are offered: the machine fetches the model itself.