Written by Jakub Rusinowski · Last updated September 19, 2026
Model library → Apertus → Apertus 70B
The flagship Apertus. At Q4 it needs a 48 GB card or a large-memory unified machine.
Apertus 70B needs about 43 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
| Parameters | 70 Billion |
| Context window | 65,536 |
| Architecture | Dense |
| Provider | EPFL / ETH Zurich / CSCS |
| Licence | Apache 2.0 |
| Specified at | Q4_K_M |
| System RAM | 64 GB |
| Record updated | 2026-09-19 |
Corroborated — Two or more independent sources agree on these figures, but the model card itself was not retrieved. Treat the numbers as good rather than confirmed. Still unconfirmed: context, releaseDate, hfModelId.
Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB). Weights plus framework overhead only — this model publishes no architecture we can read, so no KV cache is included. A real session needs more; the figure is a floor, not a target. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Bits/weight | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|---|
| Q2_K | 2.63 | 23 GB | 23.8 GB | ~29 tok/s (est.) | Tight fit |
| Q3_K_M | 3.41 | 29.8 GB | 30.6 GB | ~3 tok/s (est.) | Offloads to system RAM (slow) |
| Q4_K_M | 4.83 | 42.3 GB | 43.1 GB | ~3 tok/s (est.) | Offloads to system RAM (slow) |
| Q5_K_M | 5.67 | 49.6 GB | 50.4 GB | ~2 tok/s (est.) | Offloads to system RAM (slow) |
| Q6_K | 6.56 | 57.4 GB | 58.2 GB | — | Won't fit |
| Q8_0 | 8.50 | 74.4 GB | 75.2 GB | — | Won't fit |
| F16 | 16.00 | 140 GB | 140.8 GB | — | Won't fit |
Want to set your own context length and KV-cache quantization? Use the interactive VRAM calculator.
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
The cheapest catalogued GPU that runs Apertus 70B is the Apple M5 Pro (64 GB).
Install Ollama, then run:
ollama run apertusWeights on Hugging Face: swiss-ai/Apertus-70B.
Best for: multilingual, european languages, low resource languages, research.
← All Apertus models | VRAM calculator | Check your own hardware