Can I run Hy4 Flash locally?
Hy4 Flash by tencent has 220B parameters (4.4B active per token, 512 experts, 16 used per token). At 4-bit with an 8K context it needs about 126 GB of GPU memory. It fits on 9 of 65 GPUs and Macs we track.
This model uses a newer compressed or sparse attention design. Our KV-cache numbers use the standard formula, so treat long-context figures as an upper bound.
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 | 77.6 GB | 77.7 GB | 78.1 GB | 79.6 GB |
| 3-bit (Q3_K_M) | usable | 101 GB | 101 GB | 101 GB | 103 GB |
| 4-bit (Q4_K_M) | good, most popular | 126 GB | 126 GB | 127 GB | 128 GB |
| 5-bit (Q5_K_M) | very good | 147 GB | 147 GB | 147 GB | 149 GB |
| 6-bit (Q6_K) | near lossless | 169 GB | 169 GB | 169 GB | 171 GB |
| 8-bit (Q8_0) | effectively lossless | 219 GB | 219 GB | 219 GB | 221 GB |
| 16-bit (F16/BF16) | original weights | 411 GB | 411 GB | 411 GB | 413 GB |
Which GPUs and Macs run Hy4 Flash?
Short answer with CPU offload and RAM needed: Can I run Hy4 Flash on my PC?
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: Hy4 flash is on OpenRouter at $0.035 per 1M input tokens and $0.141 per 1M output tokens. Price details and history →
Questions
How much VRAM does Hy4 Flash need?
About 126 GB at 4-bit (Q4_K_M) with an 8K context: 125 GB of weights (estimated), 0.1 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 219 GB.
What is the smallest GPU that runs Hy4 Flash?
No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the Mac M2 Ultra 192GB (192 GB).
Can I run Hy4 Flash on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M2 Ultra 192GB 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.
Hy4 Flash Base
219B · 126 GB at 4-bitHy3
299B · 173 GB at 4-bitHy3 Preview
299B · 173 GB at 4-bitMiniMax M3.1 Flash
220B · 127 GB at 4-bitMiniMax M2.5
229B · 132 GB at 4-bitMiniMax M2.7
229B · 132 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/hy4-flash/) Widget (script)
<div class="runsonmy-widget" data-model="hy4-flash"><a href="https://runsonmy.com/model/hy4-flash/">Will Hy4 Flash 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/hy4-flash/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will Hy4 Flash run on my GPU? (RunsOnMy)"></iframe> Model facts
| Hugging Face repo | tencent/Hy4-flash |
| Parameters | 220,251,201,958 (220B) · ~4.4B active (computed from config), low confidence, speed not shown |
| Layers / hidden size | 42 / 3072 |
| Attention | MLA; 32 heads, 32 KV heads, head dim 64; sliding window 512 |
| KV cache per token (FP16) | 16.5 KiB |
| Max context | 1,048,576 tokens |
| License | other |
| Released on HF | Nov 17, 2026 |
| Downloads (30d) / likes | 0 / 73 |
Sources: Hugging Face model API · config.json (tencent/Hy4-flash) · GPU specs from vendor pages (list). Data fetched Nov 18, 2026. Spot an error? Report it.