Hy3 Preview — Hardware Requirements & GPU Compatibility
Chat
Hy3 Preview is a 298.8B-parameter open language model from tencent. It supports a context window of up to 262,144 tokens. At BF16 it needs about 598.21 GB of VRAM — see which GPUs and Macs can run it below.
90.2K downloads
269 likesSpecifications
- Publisher
- tencent
- Parameters
- 298.8B
- Architecture
- HYV3ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 120,832
- Release Date
- 2026-04-23
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Hy3 Preview Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 598.2 GB | 640.8 GB | 597.57 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Hy3 Preview?
BF16 · 598.2 GBHy3 Preview (BF16) requires 598.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 778+ GB is recommended. Using the full 262K context window can add up to 42.6 GB, bringing total usage to 640.8 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Hy3 Preview?
BF16 · 598.2 GB2 devices with unified memory can run Hy3 Preview, including NVIDIA DGX H100.
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Hy3 Preview need?
Hy3 Preview requires 598.2 GB of VRAM at BF16. Full 262K context adds up to 42.6 GB (640.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 298.8B × 16 bits ÷ 8 = 597.6 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 43.2 GB (at full 262K context)
VRAM usage by quantization
BF16598.2 GBBF16 + full context640.8 GB- Can NVIDIA GeForce RTX 5090 run Hy3 Preview?
No — Hy3 Preview requires at least 598.2 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Hy3 Preview on a Mac?
Hy3 Preview requires at least 598.2 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Hy3 Preview locally?
Yes — Hy3 Preview can run locally on consumer hardware. At BF16 quantization it needs 598.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- What's the download size of Hy3 Preview?
At BF16, the download is about 597.57 GB.
- Which GPUs can run Hy3 Preview?
No single consumer GPU has enough VRAM to run Hy3 Preview at BF16 (598.2 GB). Multi-GPU or professional hardware is required.
- Which devices can run Hy3 Preview?
2 devices with unified memory can run Hy3 Preview at BF16 (598.2 GB), including NVIDIA DGX A100 640GB, NVIDIA DGX H100. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.