Apertus v1.5 70B needs ~57.7 GB VRAM. NVIDIA H100 80GB has 80.0 GB. With Q4_K_M quantization, expect ~64 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
69.7 tok/s
TTFT
2779 ms
Safe context
89K
Memory
57.7 GB / 80.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 64.1 tok/s | 1648 ms | 89K |
| Coding | A | Runs well | 64.1 tok/s | 3022 ms | 89K |
| Agentic Coding | A | Runs well | 64.1 tok/s | 4395 ms | 89K |
| Reasoning | A | Runs well | 64.1 tok/s | 3571 ms | 89K |
| RAG | A | Runs well | 64.1 tok/s | 5494 ms | 89K |
Inference speed
Estimated decode speed (tokens/sec) for Apertus v1.5 70B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is 2× RX 7900 XTX 24GB at ~17 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
2× RX 7900 XTX 24GB | 48 GB | Q4_K_M | 16.7 | Heavy offload |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 14.9 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 13.8 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 11.5 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 11.0 | Too big |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 10.9 | Fits |
 2× RTX 4090 24GB | 48 GB | Q4_K_M | 8.8 | Heavy offload |
| 2× RTX 3090 24GB | 48 GB | Q4_K_M | 8.1 | Heavy offload |
| 4× RTX 3060 12GB | 48 GB | Q4_K_M | 7.1 | Heavy offload |
| RTX 5090 32GB | 32 GB | Q4_K_M | 5.3 | Too big |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 5.1 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 4.4 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 4.0 | Too big |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 2.6 | Too big |
| RTX 4090 24GB | 24 GB | Q4_K_M | 2.0 | Too big |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 2.0 | Too big |
| RTX 3090 24GB | 24 GB | Q4_K_M | 2.0 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.0 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How Apertus v1.5 70B (72B params) fits at each quantization level on NVIDIA H100 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q1_0_G128 | 1.125 | 10.4 GB | Very Low | B70 |
Q2_0_G128 | 1.71 | 19.2 GB | Low | A71 |
Q2_K | 2 | 28.1 GB | Low | A73 |
Q3_K_S | 3 | 35.3 GB | Low | A75 |
NVFP4 | 4 | 40.3 GB | Medium | A76 |
Q4_K_M | 4 | 43.9 GB | Medium | A77 |
Q5_K_M | 5 | 51.8 GB | High | A77 |
Q6_KBest for your GPU | 6 | 59.0 GB | High | A77 |
Q8_0 | 8 | 77.0 GB | Very High | F0 |
F16 | 16 | 147.6 GB | Maximum | F0 |
Copy-paste commands to run Apertus v1.5 70B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "swiss-ai/Apertus-v1.5-70B" \
--hf-file "Apertus-v1.5-70B-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Devstral 2 123B Instruct | 123B | A | 29 tok/s | |
 Qwen 3.5 122B A10B | 122B | A | 86 tok/s | |
 Command A 111B | 111B | S | 38.3 tok/s | |
| Pixtral Large 124B | 124B | A | 28.5 tok/s | |
 GPT-OSS 120B | 117B | A | 33 tok/s |
Yes, NVIDIA H100 80GB can run Apertus v1.5 70B with a A grade (Runs well). Expected decode speed: 64.1 tok/s.
Apertus v1.5 70B (72B parameters) requires approximately 57.7 GB of memory with Q4_K_M quantization.
The recommended quantization for Apertus v1.5 70B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA H100 80GB, Apertus v1.5 70B achieves approximately 64.1 tokens per second decode speed with a time-to-first-token of 3022ms using Q4_K_M quantization.
For coding workloads, Apertus v1.5 70B on NVIDIA H100 80GB receives a A grade with 64.1 tok/s and 89K context.
On NVIDIA H100 80GB, Apertus v1.5 70B can safely use up to 89K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/apertus-v1.5-70b-on-h100-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: