llmrun
nex-agiQwen3_5MoeForConditionalGeneration

Nex N2 Pro — Hardware Requirements & GPU Compatibility

Chat

Nex N2 Pro is a 396.8B-parameter open language model from nex-agi. It supports a context window of up to 262,144 tokens. At BF16 it needs about 794.03 GB of VRAM — see which GPUs and Macs can run it below.

396.8B params · MoE18B active262K contextApache 2.0973 downloads376 likes

Nex N2 Pro runs on a multi-GPU server

BF16 needs ~794.2 GB · about 7× H200 SXM 141 GB

Apache 2.0

Not set up for it?

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Nex N2 Pro

One recommended way. Every other method, OS and quant is in the step-by-step guide.

Recommended

vLLM on a multi-GPU server
tensor + pipeline parallel · needs vLLM on every node
$vllm serve nex-agi/Nex-N2-Pro --max-model-len 16384 --tensor-parallel-size 8

Size the nodes from the table above

Download: Weights on Hugging Face

install, other ways

Other ways

each opens step-by-step

Run in cloud

Rent 7× H200 SXM · BF16

Estimated hourly price
~$25.13/hr
est., whole server
GPUs
7 GPUs
987 GB of VRAM

How Much VRAM Does Nex N2 Pro Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KRuns on
794.0 GB794.4 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingRuns on 7× H200 SXM 141 GB
est.calculated, no published file yet

Selected BF16

Brain floating point 16

794.2GBat 16K context

Weights
793.6 GB
KV cache
0.3 GB
Overhead
0.3 GB

Server-class: ~794.2 GB at 16K context · about 7× H200 SXM 141 GB

Which Hardware Can Run Nex N2 Pro?

BF16 · 794.0 GB

Nex N2 Pro (BF16) requires 794.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1033+ GB is recommended. Using the full 262K context window can add up to 3.9 GB, bringing total usage to 797.9 GB. No consumer GPU has enough memory.

Needs server-class hardware

Nex N2 Pro runs on a multi-GPU server · BF16 needs ~794.2 GB

Hardware that runs this model
HardwareQuantMemoryContextHardware page
7× H200 SXM 141 GB · 987 GBBF16794.2 GB256K ctxH200 SXM →BF16 · 794.2 GB · 256K ctx
5× B200 192 GB · 960 GBBF16794.2 GB256K ctxB200 →BF16 · 794.2 GB · 256K ctx

≤ 640 GB tier →

By VRAM tier · typical GPUs and Macs at BF16

Consumer GPUs (up to 32 GB) and Macs up to 512 GB: too small for this model (needs ≥ 794.2 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →

Alternatives to Nex N2 Pro

Similar models

6
ModelScoreVRAMWhy it is similar
Qwen3.5 397B A17BAlibaba113.0242.6 GBsame size
MiniMax M3MiniMax112.5258 GBsame size
Llama 4 Maverick 17B 128E InstructMeta87.1272.7 GBsame size
Llama 3.1 405B InstructMeta83.2275.6 GBsame size
Intern S2 397BInternLM—242.6 GBsame size
Ornith 1.5 397Bornith-ai—242.6 GBsame size

Specifications

Publisher
nex-agi
Parameters
396.8B
Active parameters
17.8B per token
Architecture
Qwen3_5MoeForConditionalGeneration
Context Length
262,144 tokens
Vocabulary Size
248,320
Release Date
2026-06-03
License
Apache 2.0

Frequently Asked Questions

How much VRAM does Nex N2 Pro need?

Nex N2 Pro requires 794.0 GB of VRAM at BF16. Full 262K context adds up to 3.9 GB (797.9 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 396.8B × 16 bits ÷ 8 = 793.6 GB

KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

KV Cache + Overhead ≈ 4.3 GB (at full 262K context)

VRAM usage by quantization

794.0 GB
797.9 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 5090 run Nex N2 Pro?

No — Nex N2 Pro requires at least 794.0 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.

Can I run Nex N2 Pro on a Mac?

Nex N2 Pro requires at least 794.0 GB at BF16. None of the 146 Macs we list has that much usable memory (the largest has 508.5 GB after macOS overhead).

Can I run Nex N2 Pro locally?

Yes — Nex N2 Pro can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

What's the download size of Nex N2 Pro?

At BF16, the download is about 793.60 GB.

Which GPUs can run Nex N2 Pro?

No single consumer GPU has enough VRAM to run Nex N2 Pro at BF16 (794.0 GB). Multi-GPU or professional hardware is required.

Which devices can run Nex N2 Pro?

Nex N2 Pro requires at least 794.0 GB at BF16, which exceeds the usable memory of every unified-memory device we list (the largest has 508.5 GB).