Aiqre

Model library / Qwen

Qwen3.8-2.4T-A95B

Qwen3.8-2.4T-A95B is a 2.4 trillion-parameter causal language model with 95 billion active parameters, supporting up to 262 k token context.

2446.2B

Mixture of experts, count not published

262,144

Context length in tokens, as published

4556 GiB

Weights at the released precision

other

Licence declared on the repository

Overview

What this model is.

Qwen3.8-2.4T-A95B is a causal language model from Qwen, built on the Qwen3.5 architecture and post-trained for coding, professional work, research and long-horizon agentic tasks. The publisher highlights improved autonomous planning, flexible reasoning control and broad compatibility with development tools and ease of integration into existing pipelines.

The model contains 2.4 trillion parameters overall, with 95 billion activated per inference, organised in 92 layers and a hidden dimension of 8192. It uses a mixture of 512 experts, routing ten plus one shared per token, and runs in bfloat16 format. Native context length is 262 k tokens, extendable to about one million, and it is released under a non-standard licence.

Specification

The published shape.

RepositoryQwen/Qwen3.8-2.4T-A95B
PublisherQwen
Published8 August 2026
ArchitectureQwen3_5MoeForCausalLM
Model typeqwen3_5_moe_text
Parameters2,446,182,725,504
Layers92
Hidden size8,192
Attention heads64, 4 key/value heads
Context length262,144 tokens
Vocabulary248,320 tokens
Weight formatbfloat16
Licenceother

Memory

How much VRAM the weights need.

Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.

PrecisionWeightsNotes
bf164556.4 GiBFull precision as released
fp82278.2 GiB8-bit, near-lossless on most models
int41139.1 GiB4-bit, smallest footprint

The cache costs 368 KiB per token at 16-bit, so the full 262,144-token context of one request needs about 92.0 GiB. Concurrency multiplies that number, not the weights.

Hardware

Which card runs it.

At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.

GPUCards neededFree for cacheContext it holds
RTX 4090 24GB more than 8
RTX 5090 32GB more than 8
L40S 48GB more than 8
A100 80GB more than 8
H100 80GB more than 8
RTX PRO 6000 96GB more than 8
H200 141GB more than 8

Serving

Running it yourself.

A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.

vllm serve Qwen/Qwen3.8-2.4T-A95B \
  --tensor-parallel-size 8 \
  --max-model-len 262144 \
  --gpu-memory-utilization 0.90

At the released precision the weights do not fit on eight of the largest cards above, so this needs more than one node, or a quantised build.

Questions

The things people ask about this model.

How much GPU memory does Qwen3.8-2.4T-A95B need?

The weights take about 4556 GiB at the released precision. No single card in the table above holds that, so it needs several GPUs or a lower precision.

What licence does Qwen3.8-2.4T-A95B use?

The repository declares other. Read the licence text before commercial use: the name alone does not tell you what is allowed.

How long a context does it support?

The configuration allows 262,144 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.

Can I use it through an API instead of hosting it?

This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.

Also in the library

Related models.

nex-agi/Nex-N2.5-Max

Nex-N2.5-Max is a 1.6-trillion-parameter text-only MoE model designed for long-horizon agentic tasks.

deepseek-ai/DeepSeek-V4-Pro-0813

DeepSeek-V4-Pro-0813 is a 1650.5B mixture-of-experts open-weight model published by deepseek-ai on Hugging Face. It uses the Deep…

Hosting

Want this model on a dedicated EU GPU?

Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.