Apertus 70B Instruct 2509 — Hardware Requirements & GPU Compatibility
Chat
Apertus 70B Instruct 2509 is a 70B-parameter open language model from swiss-ai in the Apertus family. It supports a context window of up to 65,536 tokens. At Q4_K_M it needs about 42.97 GB of VRAM — see which GPUs and Macs can run it below.
4.9K downloads
182 likesSpecifications
- Publisher
- swiss-ai
- Family
- Apertus
- Parameters
- 70B
- Architecture
- ApertusForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2025-09-01
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Apertus 70B Instruct 2509 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 30.7 GB | 51.5 GB | 29.75 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 35.1 GB | 55.9 GB | 34.13 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 43.0 GB | 63.8 GB | 42.00 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 50.9 GB | 71.7 GB | 49.88 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 58.7 GB | 79.5 GB | 57.75 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 71.0 GB | 91.8 GB | 70.00 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 141.0 GB | 161.8 GB | 140.00 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Apertus 70B Instruct 2509?
Q4_K_M · 43.0 GBApertus 70B Instruct 2509 (Q4_K_M) requires 43.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 56+ GB is recommended. Using the full 66K context window can add up to 20.8 GB, bringing total usage to 63.8 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Apertus 70B Instruct 2509?
Q4_K_M · 43.0 GB27 devices with unified memory can run Apertus 70B Instruct 2509, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (64 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Apertus 70B Instruct 2509 need?
Apertus 70B Instruct 2509 requires 43.0 GB of VRAM at Q4_K_M, or 141.0 GB at BF16. Full 66K context adds up to 20.8 GB (63.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 70B × 4.8 bits ÷ 8 = 42 GB
KV Cache + Overhead ≈ 1 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 21.8 GB (at full 66K context)
VRAM usage by quantization
Q4_K_M43.0 GBQ4_K_M + full context63.8 GB- Can NVIDIA GeForce RTX 5090 run Apertus 70B Instruct 2509?
Yes, at Q2_K (30.7 GB) or lower. Higher quantizations like Q3_K_M (35.1 GB) exceed the NVIDIA GeForce RTX 5090's 32 GB.
- What's the best quantization for Apertus 70B Instruct 2509?
For Apertus 70B Instruct 2509, Q4_K_M (43.0 GB) offers the best balance of quality and VRAM usage. Q5_K_M (50.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 30.7 GB.
VRAM requirement by quantization
Q2_K30.7 GBQ4_K_M ★43.0 GBQ5_K_M50.9 GBQ6_K58.7 GBQ8_071.0 GBBF16141.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Apertus 70B Instruct 2509 on a Mac?
Apertus 70B Instruct 2509 requires at least 30.7 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Apertus 70B Instruct 2509 locally?
Yes — Apertus 70B Instruct 2509 can run locally on consumer hardware. At Q4_K_M quantization it needs 43.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Apertus 70B Instruct 2509?
At Q4_K_M, Apertus 70B Instruct 2509 can reach ~102 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 43.0 × 0.65 = ~121 tok/s
Estimated speed at Q4_K_M (43.0 GB)
~121 tok/s~121 tok/s~102 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Apertus 70B Instruct 2509?
At Q4_K_M, the download is about 42.00 GB. The full-precision BF16 version is 140.00 GB. The smallest option (Q2_K) is 29.75 GB.
- Which GPUs can run Apertus 70B Instruct 2509?
No single consumer GPU has enough VRAM to run Apertus 70B Instruct 2509 at Q4_K_M (43.0 GB). Multi-GPU or professional hardware is required.
- Which devices can run Apertus 70B Instruct 2509?
27 devices with unified memory can run Apertus 70B Instruct 2509 at Q4_K_M (43.0 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.