Hydrogen 1.0 MXFP4 — Hardware Requirements & GPU Compatibility
ChatFunctions
Hydrogen 1.0 MXFP4 is a 384.3B-parameter open language model from deep-principle. It supports a context window of up to 1,048,576 tokens. At BF16 it needs about 772.90 GB of VRAM — see which GPUs and Macs can run it below.
Hydrogen 1.0 MXFP4 runs on a multi-GPU server
BF16 needs ~770.5 GB · about 7× H200 SXM 141 GB
MIT
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Hydrogen 1.0 MXFP4
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 deep-principle/Hydrogen-1.0-MXFP4 --max-model-len 16384 --tensor-parallel-size 8Size the nodes from the table above
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Rent 7× H200 SXM · BF16
- Estimated hourly price
- ~$25.13/hr
- est., whole server
- GPUs
- 7 GPUs
- 987 GB of VRAM
$5+ bonus for new users
How Much VRAM Does Hydrogen 1.0 MXFP4 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 772.9 GB | 771.9 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 7× H200 SXM 141 GB |
Selected BF16
Brain floating point 16770.5GBat 16K context
- Weights
- 768.7 GB
- KV cache
- 1.5 GB
- Overhead
- 0.3 GB
Server-class: ~770.5 GB at 16K context · about 7× H200 SXM 141 GB
Which Hardware Can Run Hydrogen 1.0 MXFP4?
BF16 · 772.9 GBHydrogen 1.0 MXFP4 (BF16) requires 772.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1005+ GB is recommended. Using the full 1049K context window can add up to 90.3 GB, bringing total usage to 863.2 GB. No consumer GPU has enough memory.
Needs server-class hardware
Hydrogen 1.0 MXFP4 runs on a multi-GPU server · BF16 needs ~770.5 GB
| Hardware | Quant | Memory | Context | Hardware page | |
|---|---|---|---|---|---|
| 7× H200 SXM 141 GB · 987 GB | BF16 | 770.5 GB | 1M ctx | H200 SXM → | BF16 · 770.5 GB · 1M ctx |
| 5× B200 192 GB · 960 GB | BF16 | 770.5 GB | 1M ctx | B200 → | BF16 · 770.5 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 ≥ 770.5 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.5 397B A17BAlibaba | 112.8 | 242.6 GB | —needs > 24 GB | same size |
| GLM 4.6Z.ai | 103.1 | 216.9 GB | —needs > 24 GB | same size |
| Llama 4 Maverick 17B 128E InstructMeta | 87.1 | 272.7 GB | —needs > 24 GB | same size |
| Llama 3.1 405B InstructMeta | 83.5 | 275.6 GB | —needs > 24 GB | same size |
| Intern S2 397BInternLM | — | 242.6 GB | —needs > 24 GB | same size |
| Ornith 1.5 397Bornith-ai | — | 242.6 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- deep-principle
- Parameters
- 384.3B
- Architecture
- GlmMoeDsaForCausalLM
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 154,880
- Release Date
- 2026-10-31
- License
- MIT
Frequently Asked Questions
How much VRAM does Hydrogen 1.0 MXFP4 need?
Hydrogen 1.0 MXFP4 requires 772.9 GB of VRAM at BF16. Full 1049K context adds up to 90.3 GB (863.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 384.3B × 16 bits ÷ 8 = 768.7 GB
KV Cache + Overhead ≈ 4.2 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 ≈ 94.5 GB (at full 1049K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Hydrogen 1.0 MXFP4?
No — Hydrogen 1.0 MXFP4 requires at least 772.9 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Hydrogen 1.0 MXFP4 on a Mac?
Hydrogen 1.0 MXFP4 requires at least 772.9 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 Hydrogen 1.0 MXFP4 locally?
Yes — Hydrogen 1.0 MXFP4 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of Hydrogen 1.0 MXFP4?
At BF16, the download is about 768.67 GB.
Which GPUs can run Hydrogen 1.0 MXFP4?
No single consumer GPU has enough VRAM to run Hydrogen 1.0 MXFP4 at BF16 (772.9 GB). Multi-GPU or professional hardware is required.
Which devices can run Hydrogen 1.0 MXFP4?
Hydrogen 1.0 MXFP4 requires at least 772.9 GB at BF16, which exceeds the usable memory of every unified-memory device we list (the largest has 508.5 GB).