RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?API pricesVRAM calculatorNew

Can I run Apertus v1.5 8B locally?

Apertus v1.5 8B by swiss-ai has 8.9B parameters. At 4-bit with an 8K context it needs about 6.7 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 8 GB of VRAM.

6.7 GBQ4_K_M · 8K context
RTX 4060smallest consumer GPU that fits
M1 16GBsmallest Mac that fits
256Kmax context
GQAattention type

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.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K)rough4.3 GB4.8 GB7.8 GB19.8 GB
3-bit (Q3_K_M)usable5.2 GB5.7 GB8.7 GB20.7 GB
4-bit (Q4_K_M)good, most popular6.2 GB6.7 GB9.7 GB21.7 GB
5-bit (Q5_K_M)very good7.1 GB7.6 GB10.6 GB22.6 GB
6-bit (Q6_K)near lossless7.9 GB8.4 GB11.4 GB23.4 GB
8-bit (Q8_0)effectively lossless10.0 GB10.5 GB13.5 GB25.5 GB
16-bit (F16/BF16)original weights17.7 GB18.2 GB21.2 GB33.2 GB

Which GPUs and Macs run Apertus v1.5 8B?

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).

HardwareMemoryFits?Best quantNeedsMax tok/s (est.)Details
RTX 3060 12GB12 GBFitsQ6_K8.4 GB49details
RTX 4060 Ti 16GB16 GBFitsQ8_010.5 GB30details
RTX 309024 GBFitsF1618.2 GB53details
RTX 409024 GBFitsF1618.2 GB57details
RTX 509032 GBFitsF1618.2 GB101details
RTX 5070 Ti16 GBFitsQ8_010.5 GB95details
RX 7900 XTX24 GBFitsF1618.2 GB54details
Mac M4 Pro 48GB48 GBFitsF1618.2 GB15details
Mac M4 Max 128GB128 GBFitsF1618.2 GB31details
Mac M3 Ultra 512GB512 GBFitsF1618.2 GB46details
DGX Spark128 GBFitsF1618.2 GB15details
RTX 407012 GBFitsQ6_K8.4 GB69details
RTX 5060 Ti 16GB16 GBFitsQ8_010.5 GB47details
RTX 40608 GBFitsQ4_K_M6.7 GB50details
Arc B58012 GBFitsQ6_K8.4 GB62details
RTX 3060 Ti8 GBFitsQ4_K_M6.7 GB82details
RTX 30708 GBFitsQ4_K_M6.7 GB82details
RTX 3080 10GB10 GBFitsQ6_K8.4 GB104details
RTX 3080 12GB12 GBFitsQ6_K8.4 GB125details
RTX 3090 Ti24 GBFitsF1618.2 GB57details
RTX 4060 Ti 8GB8 GBFitsQ4_K_M6.7 GB53details
RTX 4070 Super12 GBFitsQ6_K8.4 GB69details
RTX 4070 Ti12 GBFitsQ6_K8.4 GB69details
RTX 4070 Ti Super16 GBFitsQ8_010.5 GB71details
RTX 408016 GBFitsQ8_010.5 GB76details
RTX 4080 Super16 GBFitsQ8_010.5 GB78details
RTX 50608 GBFitsQ4_K_M6.7 GB82details
RTX 507012 GBFitsQ6_K8.4 GB92details
RTX 508016 GBFitsQ8_010.5 GB101details
2x RTX 30902×24 GBFitsF1618.2 GB53details
2x RTX 40902×24 GBFitsF1618.2 GB57details
2x RTX 50902×32 GBFitsF1618.2 GB101details
RTX A600048 GBFitsF1618.2 GB43details
RTX 6000 Ada48 GBFitsF1618.2 GB54details
RTX PRO 6000 Blackwell96 GBFitsF1618.2 GB101details
L40S48 GBFitsF1618.2 GB49details
A100 40GB40 GBFitsF1618.2 GB87details
A100 80GB80 GBFitsF1618.2 GB115details
H100 PCIe80 GBFitsF1618.2 GB112details
H100 SXM80 GBFitsF1618.2 GB188details
H200141 GBFitsF1618.2 GB270details
RX 76008 GBFitsQ4_K_M6.7 GB53details
RX 7700 XT12 GBFitsQ6_K8.4 GB59details
RX 7800 XT16 GBFitsQ8_010.5 GB66details
RX 7900 GRE16 GBFitsQ8_010.5 GB61details
RX 7900 XT20 GBFitsQ8_010.5 GB85details
RX 907016 GBFitsQ8_010.5 GB68details
RX 9070 XT16 GBFitsQ8_010.5 GB68details
Ryzen AI Max+ 395 128GB128 GBFitsF1618.2 GB14details
Arc A770 16GB16 GBFitsQ8_010.5 GB59details
Mac M1 16GB16 GBFitsQ6_K8.4 GB9.3details
Mac M2 24GB24 GBFitsQ8_010.5 GB11details
Mac M3 24GB24 GBFitsQ8_010.5 GB11details
Mac M4 16GB16 GBFitsQ6_K8.4 GB16details
Mac M4 32GB32 GBFitsF1618.2 GB6.7details
Mac M1 Pro 32GB32 GBFitsF1618.2 GB11details
Mac M3 Pro 36GB36 GBFitsF1618.2 GB8.4details
Mac M4 Pro 24GB24 GBFitsQ8_010.5 GB29details
Mac M4 Pro 64GB64 GBFitsF1618.2 GB15details
Mac M1 Max 64GB64 GBFitsF1618.2 GB22details
Mac M2 Max 96GB96 GBFitsF1618.2 GB22details
Mac M3 Max 128GB128 GBFitsF1618.2 GB22details
Mac M4 Max 64GB64 GBFitsF1618.2 GB31details
Mac M2 Ultra 192GB192 GBFitsF1618.2 GB45details
Mac M3 Ultra 256GB256 GBFitsF1618.2 GB46details

Questions

How much VRAM does Apertus v1.5 8B need?

About 6.7 GB at 4-bit (Q4_K_M) with an 8K context: 5.1 GB of weights (estimated), 1.0 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 10.5 GB.

What is the smallest GPU that runs Apertus v1.5 8B?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 4060 (8 GB).

Can I run Apertus v1.5 8B on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M1 16GB 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 8B Instruct 2509

8.1B · 6.4 GB at 4-bit

Apertus v1.5 70B

72B · 44.4 GB at 4-bit

InternLM3 8B Instruct

8.8B · 6.0 GB at 4-bit

Granite 4.2 8B

8.8B · 6.8 GB at 4-bit

Granite 4.1 8B

8.8B · 6.8 GB at 4-bit

Granite 4.1 8B Llmon Preview

8.8B · 6.8 GB at 4-bit

Embed this

Apertus v1.5 8B: runs on 8 GB+ VRAM 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

[![Apertus v1.5 8B: runs on 8 GB+ VRAM (RunsOnMy)](https://runsonmy.com/badge/apertus-v1-5-8b.svg)](https://runsonmy.com/model/apertus-v1-5-8b/)

Widget (script)

<div class="runsonmy-widget" data-model="apertus-v1-5-8b"><a href="https://runsonmy.com/model/apertus-v1-5-8b/">Will Apertus v1.5 8B 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-v1-5-8b/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will Apertus v1.5 8B run on my GPU? (RunsOnMy)"></iframe>

Model facts

Hugging Face reposwiss-ai/Apertus-v1.5-8B
Parameters8,903,547,555 (8.9B)
Layers / hidden size32 / 4096
AttentionGQA; 32 heads, 8 KV heads, head dim 128
KV cache per token (FP16)128.0 KiB
Max context262,144 tokens
Licenseapache-2.0 (gated: accept terms on Hugging Face)
Released on HFJul 24, 2026
Downloads (30d) / likes9,179 / 189

Sources: Hugging Face model API · config.json (tokimoa/apertus-v1.5-8b-mlx-bf16) · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.