Apertus 70B
By Swiss AI · Switzerland
Updated 2026-07-13
Overview
A Swiss AI joint effort (EPFL, ETH, CSCS) trained on 15T tokens covering 1000+ languages, including Swiss German and Romansh. Apache 2.0.
When to pick this model
- European data-sovereignty-critical deployments
- Applications serving French, German, Italian, or Romansh users
- Research on broadly multilingual training
- Apache-licensed alternatives to US or Chinese flagships
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 40 GB |
| Q5_K_M | 48 GB |
| Q8_0 | 75 GB |
| FP16 (no quantization) | 140 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
In practice, Apertus 70B spills past single consumer GPUs even at Q4_K_M (40 GB) — think dual-GPU or workstation cards. Stepping up to Q8_0 nearly doubles the footprint to 75 GB, and unquantized FP16 weights take 140 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Apertus 70B needs roughly 64 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 1 tokens/sec on entry-level GPUs, on the order of 6 tokens/sec on a mid-range card, and up to 20 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Apertus 70B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for Apertus 70B |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Does not fit — needs 40 GB at Q4_K_M |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Does not fit — needs 40 GB at Q4_K_M |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | Does not fit — needs 40 GB at Q4_K_M |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | Does not fit — needs 40 GB at Q4_K_M |
| 32 GB | RTX 5090 | Does not fit — needs 40 GB at Q4_K_M |
Which GPU should you buy to run Apertus 70B?
To run Apertus 70B locally at Q4, you need ~40 GB of VRAM. The best value for this is a Apple Mac Studio (64+ GB unified memory).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Strengths
- European data sovereignty story
- Only flagship model with native Romansh support
- Apache 2.0 license
- Strong across Alpine and broader European languages
Limitations
- Around 40 GB VRAM at Q4 — multi-GPU required
- Smaller fine-tune ecosystem than Llama or Qwen
- English performance trails best-in-class US models
Typical workloads
In our catalog grid, Apertus 70B is filed under Swiss Sovereignty, Extreme Multilingual — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: multilingual workloads; French-language output where quality matters.
The 64k-token context window covers long chats and mid-sized documents, though very large retrieval workloads will need chunking. The Apache 2.0 license is permissive, so shipping it inside a commercial product raises no special legal questions.
Architecture & training
Architecture: Dense · 70B · Swiss AI Initiative · European sovereignty
Training: Swiss AI — sovereign European data, strong in FR/DE/IT/RM (Romansh).
Europe's most credible sovereign open flagship — pick it when language coverage or data jurisdiction matters more than raw English benchmarks.
Quick start
ollama pull hf.co/swissai/Apertus-70B-GGUFOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Similar models worth comparing
Frequently asked questions
How much VRAM does Apertus 70B need?
At the recommended Q4_K_M quantization, Apertus 70B needs about 40 GB of VRAM. Q8_0 takes 75 GB, and unquantized FP16 weights take 140 GB.
Can Apertus 70B run without a GPU?
Yes — with roughly 64 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does Apertus 70B support?
Apertus 70B supports a 64k-token context window (65,536 tokens).
Can I use Apertus 70B commercially?
Yes. Apertus 70B is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.
How fast is Apertus 70B on consumer hardware?
Our compatibility engine estimates on the order of 6 tokens/sec on a mid-range GPU and up to 20 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Apertus 70B should I download first?
Start with Q4_K_M (40 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It does not fit a single 24 GB consumer card — plan for multi-GPU or server hardware.