Can I run Hy3 Preview locally?
Hy3 Preview by tencent has 299B parameters (21B active per token, 192 experts, 8 used per token). At 4-bit with an 8K context it needs about 173 GB of GPU memory. It fits on 6 of 65 GPUs and Macs we track.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx | 32K ctx | 128K ctx |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | rough | 106 GB | 107 GB | 115 GB | 145 GB |
| 3-bit (Q3_K_M) | usable | 138 GB | 139 GB | 147 GB | 177 GB |
| 4-bit (Q4_K_M) | good, most popular | 172 GB | 173 GB | 181 GB | 211 GB |
| 5-bit (Q5_K_M) | very good | 200 GB | 201 GB | 209 GB | 239 GB |
| 6-bit (Q6_K) | near lossless | 230 GB | 231 GB | 239 GB | 269 GB |
| 8-bit (Q8_0) | effectively lossless | 298 GB | 299 GB | 306 GB | 336 GB |
| 16-bit (F16/BF16) | original weights | 558 GB | 560 GB | 567 GB | 597 GB |
Which GPUs and Macs run Hy3 Preview?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
Prefer an API?
Tencent: Hy3 preview is on OpenRouter at $0.18 per 1M input tokens and $0.60 per 1M output tokens. Price details and history →
Questions
How much VRAM does Hy3 Preview need?
About 173 GB at 4-bit (Q4_K_M) with an 8K context: 170 GB of weights (estimated), 2.5 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 299 GB.
What is the smallest GPU that runs Hy3 Preview?
No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the Mac M3 Ultra 512GB (512 GB).
Can I run Hy3 Preview on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M3 Ultra 512GB or larger, using the default macOS GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
Hy3
299B · 173 GB at 4-bitHunyuan A13B Instruct
80B · 47.6 GB at 4-bitHy Memory 30B A3B
30B · 18.5 GB at 4-bitDeepSeek V4 Flash 0731
304B · 175 GB at 4-bitDeepSeek V4 Flash DSpark
304B · 175 GB at 4-bitDeepSeek V4 Flash Vision Exp
305B · 175 GB at 4-bitEmbed this
Free badge and "Will it run on my GPU?" widget for model cards, READMEs and blogs. No cookies, no tracking. All options.
Copy a snippet
Markdown badge
[](https://runsonmy.com/model/hy3-preview/) Widget (script)
<div class="runsonmy-widget" data-model="hy3-preview"><a href="https://runsonmy.com/model/hy3-preview/">Will Hy3 Preview run on my GPU? Check on RunsOnMy</a></div>
<script async src="https://runsonmy.com/embed.js"></script> Widget (iframe)
<iframe src="https://runsonmy.com/embed/m/hy3-preview/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will Hy3 Preview run on my GPU? (RunsOnMy)"></iframe> Model facts
| Hugging Face repo | tencent/Hy3-preview |
| Parameters | 298,786,155,776 (299B) · ~21B active (computed from config) |
| Layers / hidden size | 80 / 4096 |
| Attention | GQA; 64 heads, 8 KV heads, head dim 128 |
| KV cache per token (FP16) | 320.0 KiB |
| Max context | 262,144 tokens |
| License | other |
| Released on HF | Apr 13, 2026 |
| Downloads (30d) / likes | 100,099 / 314 |
Sources: Hugging Face model API · config.json (tencent/Hy3-preview) · GPU specs from vendor pages (list). Data fetched Nov 18, 2026. Spot an error? Report it.