Nex N2.5 Max — Hardware Requirements & GPU Compatibility
Chat
Nex N2.5 Max is a 1600.8B-parameter open language model from nex-agi. It supports a context window of up to 1,048,576 tokens. At BF16 it needs about 3201.90 GB of VRAM — see which GPUs and Macs can run it below.
Nex N2.5 Max runs on a GPU cluster
BF16 needs ~3.2 TB · about 6 nodes of 8× H100 SXM 80 GB
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Nex N2.5 Max
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve nex-agi/Nex-N2.5-Max --max-model-len 16384 --tensor-parallel-size 8 --pipeline-parallel-size <nodes>Size the nodes from the table above
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Rent 6× 8-GPU H100 SXM nodes · BF16
- Estimated hourly price
- ~$129/hr
- est., whole cluster
- GPUs
- 48 GPUs
- 3.8 TB of VRAM
$5+ bonus for new users
How Much VRAM Does Nex N2.5 Max Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 3201.9 GB | 3202.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 6 nodes of 8× H100 SXM |
Selected BF16
Brain floating point 163202.1GBat 16K context
- Weights
- 3201.6 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Server-class: ~3.2 TB at 16K context · about 6 nodes of 8× H100 SXM 80 GB
Which Hardware Can Run Nex N2.5 Max?
BF16 · 3201.9 GBNex N2.5 Max (BF16) requires 3201.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4163+ GB is recommended. Using the full 1049K context window can add up to 14.3 GB, bringing total usage to 3216.2 GB. No consumer GPU has enough memory.
Needs server-class hardware
Nex N2.5 Max runs on a GPU cluster · BF16 needs ~3.2 TB
| Hardware | Quant | Memory | Context | Hardware page | |
|---|---|---|---|---|---|
| GPU cluster · 6 nodes of 8× H100 SXM 80 GB | BF16 | 3202.1 GB | 1M ctx | H100 SXM → | BF16 · 3202.1 GB · 1M ctx |
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 ≥ 3.2 TB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Similar models
1| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| DeepSeek V4 Pro 0813DeepSeek | 129.2 | 990.8 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- nex-agi
- Parameters
- 1600.8B
- Active parameters
- 52.6B per token
- Architecture
- DeepseekV4ForCausalLM
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 129,280
- Release Date
- 2026-09-07
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Nex N2.5 Max need?
Nex N2.5 Max requires 3201.9 GB of VRAM at BF16. Full 1049K context adds up to 14.3 GB (3216.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1600.8B × 16 bits ÷ 8 = 3201.6 GB
KV Cache + Overhead ≈ 0.3 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 ≈ 14.6 GB (at full 1049K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Nex N2.5 Max?
No — Nex N2.5 Max requires at least 3201.9 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Nex N2.5 Max on a Mac?
Nex N2.5 Max requires at least 3201.9 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 N2.5 Max locally?
Yes — Nex N2.5 Max can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of Nex N2.5 Max?
At BF16, the download is about 3201.57 GB.
Which GPUs can run Nex N2.5 Max?
No single consumer GPU has enough VRAM to run Nex N2.5 Max at BF16 (3201.9 GB). Multi-GPU or professional hardware is required.
Which devices can run Nex N2.5 Max?
Nex N2.5 Max requires at least 3201.9 GB at BF16, which exceeds the usable memory of every unified-memory device we list (the largest has 508.5 GB).