Can I run Apertus v1.5 70B locally?
Apertus v1.5 70B by swiss-ai has 72B parameters. At 4-bit with an 8K context it needs about 44.4 GB of GPU memory. It fits on 25 of 65 GPUs and Macs we track. See all models that fit in 48 GB of VRAM.
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 | 27.3 GB | 28.6 GB | 36.1 GB | 66.1 GB |
| 3-bit (Q3_K_M) | usable | 34.9 GB | 36.2 GB | 43.7 GB | 73.7 GB |
| 4-bit (Q4_K_M) | good, most popular | 43.1 GB | 44.4 GB | 51.9 GB | 81.9 GB |
| 5-bit (Q5_K_M) | very good | 49.9 GB | 51.2 GB | 58.7 GB | 88.7 GB |
| 6-bit (Q6_K) | near lossless | 57.1 GB | 58.4 GB | 65.9 GB | 95.9 GB |
| 8-bit (Q8_0) | effectively lossless | 73.4 GB | 74.7 GB | 82.2 GB | 112 GB |
| 16-bit (F16/BF16) | original weights | 136 GB | 138 GB | 145 GB | 175 GB |
Which GPUs and Macs run Apertus v1.5 70B?
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).
Questions
How much VRAM does Apertus v1.5 70B need?
About 44.4 GB at 4-bit (Q4_K_M) with an 8K context: 41.0 GB of weights (estimated), 2.5 GB of KV cache and 0.9 GB of runtime overhead. At 8-bit it needs about 74.7 GB.
What is the smallest GPU that runs Apertus v1.5 70B?
No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the H100 PCIe (80 GB).
Can I run Apertus v1.5 70B on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M2 Max 96GB 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.
Apertus v1.5 8B
8.9B · 6.7 GB at 4-bitApertus 8B Instruct 2509
8.1B · 6.4 GB at 4-bitKimi Dev 72B
73B · 44.6 GB at 4-bitLlama 3.3 70B Instruct
71B · 42.7 GB at 4-bitLlama 3.1 70B Instruct
71B · 42.7 GB at 4-bitMeta Llama 3 70B Instruct
71B · 42.7 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/apertus-v1-5-70b/) Widget (script)
<div class="runsonmy-widget" data-model="apertus-v1-5-70b"><a href="https://runsonmy.com/model/apertus-v1-5-70b/">Will Apertus v1.5 70B 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/apertus-v1-5-70b/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will Apertus v1.5 70B run on my GPU? (RunsOnMy)"></iframe> Model facts
| Hugging Face repo | swiss-ai/Apertus-v1.5-70B |
| Parameters | 72,005,819,139 (72B) |
| Layers / hidden size | 80 / 8192 |
| Attention | GQA; 64 heads, 8 KV heads, head dim 128 |
| KV cache per token (FP16) | 320.0 KiB |
| Max context | 262,144 tokens |
| License | apache-2.0 (gated: accept terms on Hugging Face) |
| Released on HF | Jul 24, 2026 |
| Downloads (30d) / likes | 7,497 / 149 |
Sources: Hugging Face model API · config.json (onprem-ai/Apertus-v1.5-70B-FP8) · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.