Swiss AI · Chat and reasoning · 72B parameters · apache-2.0
Apertus v1.5 70B
Needs 87 GB at FP8 / INT8. The smallest real configuration today is 4× RTX 3090 at Clore.ai, $0.25 per hour, about $183 a month at 730 hours.
Parameters72Bdense
Context—maximum published
Checkpoint145 GBBF16, as published
Licenseapache-2.0check before commercial use
Released—documented date
Smallest configuration · FP8 / INT8
4× RTX 309096 GB VRAM · 90% used
- Per hour
- $0.25
- Per month
- $183
- Cheapest at
Clore.ai
Memory · 3 precisionsHow much VRAM it needs
Weights plus runtime overhead. The context dimension appears once the model's architecture is on file.
| Precision | Weights | Weights + headroom |
|---|---|---|
| BF16published checkpoint | 145 GB | 174 GB |
| FP8 / INT8estimated | 72 GB | 87 GB |
| INT4 / MXFP4estimated | 43 GB | 52 GB |
Cross-checked on Hugging Face Oct 28, 2026: 72.0B parameters in the safetensors headers, 144.6 GB of weight files. Method: weights as published at the native precision, verified on Hugging Face 2026-10-28; other precisions estimated at 1 (8-bit) and 0.6 (4-bit) bytes per parameter; × 1.2 runtime headroom; KV cache not added (architecture not readable).
Smallest configuration per GPU · 110 GPUs · cheapest eligible on-demand offer per GPU count, every provider on fileWhat it costs to run, GPU by GPU
The fewest GPUs of one type whose total memory fits the model at short context, priced from the cheapest eligible on-demand offer for exactly that count (45-day window, newest reading per provider), with the next providers beside it. Monthly = 730 hours.
| GPU | Smallest config | VRAM used | $ / hour | $ / month | Cheapest at |
|---|---|---|---|---|---|
| RTX 3090Best fit | 4× 24 GB96 GB total | 90% | $0.25 | $183 | Clore.aiTrust 46 · read Nov 1 · receipt · also Vast.ai $0.58, Lium $0.88 |
| Tesla V100 32GB | 4× 32 GB128 GB total | 68% | $0.27 | $196 |  Vast.aiTrust 78 · read Nov 1 · receipt · also Clore.ai $0.41, Cyfuture AI $2.22 |
| RTX A6000 | 2× 48 GB96 GB total | 90% | $0.38 | $274 | Clore.aiTrust 46 · read Nov 1 · receipt · also Lium $0.84, Spheron $0.89 |
| Tesla P100 | 8× 16 GB128 GB total | 68% | $0.38 | $274 | Vast.aiTrust 78 · read Nov 1 · receipt |
| RTX 3060 | 8× 12 GB96 GB total | 90% | $0.43 | $312 | Vast.aiTrust 78 · read Nov 1 · receipt |
| Quadro RTX 8000 | 2× 48 GB96 GB total | 90% | $0.51 | $371 | Vast.aiTrust 78 · read Nov 1 · receipt |
| L40 | 2× 48 GB96 GB total | 90% | $0.54 | $391 | Vast.aiTrust 78 · read Nov 1 · receipt · also io.net $1.32, GPU.ai $1.56 |
| RTX 2080 Ti | 8× 11 GB88 GB total | 98% tight | $0.59 | $432 | Vast.aiTrust 78 · read Nov 1 · receipt · also Edgevana $0.68 |
| RTX PRO 6000 | 1× 96 GB96 GB total | 90% | $0.66 | $482 |  packet.ainot scored · read Nov 1 · receipt · also Runpod $0.69, HyperAI $0.80 |
| Titan RTX | 4× 24 GB96 GB total | 90% | $0.70 | $508 | Vast.aiTrust 78 · read Nov 1 · receipt |
| Tesla V100 16GB | 8× 16 GB128 GB total | 68% | $0.75 | $547 | Vast.aiTrust 78 · read Nov 1 · receipt · also CloudRift $2.32, Lambda $6.32 |
| RTX 5060 Ti | 8× 16 GB128 GB total | 68% | $0.75 | $549 | Vast.aiTrust 78 · read Nov 1 · receipt · also Clore.ai $0.82, Edgevana $1.51 |
| L40S | 2× 48 GB96 GB total | 90% | $0.76 | $555 |  LiumTrust 40 · read Nov 1 · receipt · also Vast.ai $1.28, VoltageGPU $1.52 |
| RTX A5000 | 4× 24 GB96 GB total | 90% | $0.80 | $586 | Vast.aiTrust 78 · read Nov 1 · receipt |
| RTX PRO 4000 | 4× 24 GB96 GB total | 90% | $0.83 | $608 | Clore.aiTrust 46 · read Nov 1 · receipt |
| RTX A4000 | 8× 16 GB128 GB total | 68% | $0.96 | $701 | LiumTrust 40 · read Nov 1 · receipt · also Vast.ai $0.96, VoltageGPU $1.92 |
| A800 80GB PCIe | 2× 80 GB160 GB total | 54% | $0.96 | $702 | Vast.aiTrust 78 · read Nov 1 · receipt |
| RTX PRO 5000 | 2× 48 GB96 GB total | 90% | $0.96 | $702 | Vast.aiTrust 78 · read Nov 1 · receipt · also Lium $1.70, AtmosCompute $2.04 |
| RTX 4070 Super | 8× 12 GB96 GB total | 90% | $0.97 | $708 | Vast.aiTrust 78 · read Nov 1 · receipt · also Edgevana $1.23, AtmosCompute $1.75 |
| RTX 6000 Ada | 2× 48 GB96 GB total | 90% | $0.99 | $722 | Vast.aiTrust 78 · read Nov 1 · receipt · also GPU.ai $1.30, io.net $1.37 |
| Gaudi 2 | 1× 96 GB96 GB total | 90% | $1.06 | $777 |  Cyfuture AInot scored · read Nov 1 · receipt |
| L4 | 4× 24 GB96 GB total | 90% | $1.09 | $795 |  Infomaniaknot scored · read Nov 1 · receipt · also Vast.ai $1.39, OVHcloud $3.35 |
| A100 80GB | 2× 80 GB160 GB total | 54% | $1.20 | $878 | Vast.aiTrust 78 · read Nov 1 · receipt · also Thunder Compute $2.18, Spheron $2.38 |
| RTX 5070 | 8× 12 GB96 GB total | 90% | $1.21 | $882 | Clore.aiTrust 46 · read Nov 1 · receipt |
| The 24 cheapest of 61 GPU types that fit. Every GPU, any precision and context, in the finder | |||||
Throughput estimates · Oct 4, 2026Tokens per second, and what a million costs
Chat and reasoning. Speed estimated from memory bandwidth and model size, never measured. The cost per 1M output tokens is an estimate at the prices read on Oct 4, 2026; it is not recomputed here.
| GPU | Cards | Precision | tok/s per user | per 1M output tokens · estimate |
|---|---|---|---|---|
| MI300X | 1 | FP8 | 35.3 | $0.517 |
| B200 | 1 | FP8 | 64.0 | $0.657 |
| H200 | 1 | FP8 | 40.4 | $0.754 |
| H100 SXM | 2 | FP8 | 45.6 | $0.769 |
| RTX 5090 | 4 | FP8 | 32.6 | $0.965 |
| H100 PCIe | 2 | FP8 | 23.9 | $0.976 |
| RTX PRO 6000 | 1 | FP8 | 16.5 | $1.67 |
| A100 80GB | 4 | BF16 | 28.4 | $1.84 |
| RTX 4090 | 4 | FP8 | 20.5 | $2.18 |
| L40S | 2 | FP8 | 11.9 | $2.40 |
cards, precision and speed estimated from memory bandwidth and model size; cost recomputed by the site from verified prices · cheapest per output at the prices of Oct 4, 2026: MI300XWhy estimates, and their limits →
Apertus v1.5 70B · related