Apertus 70B Instruct 2509 needs about 46.9 GB of memory at Q4_K_M (a 43.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 15 quants, from 24.3 GB (IQ2_M) to 57.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Apertus 70B Instruct 2509 – a large multilingual instruction model
Apertus 70B Instruct 2509 is a 70.6B parameter decoder‑only transformer. It supports a context length of 65,536 tokens and is trained on 15T tokens with a staged curriculum of web, code and math data. The model is fully open with open weights, data and training details.
Good at
- Reasoning
- Tool use
- Long‑context processing
Limits
- No vision support
- Requires large VRAM for full precision
- Apache‑2.0 license
Best for
- Complex reasoning tasks
- Tool‑enabled agentic workflows
- Long‑form content generation
Who it’s for. Developers and researchers needing a fully open, multilingual instruction model with extensive context support. Suitable for on‑device inference with quantization or server‑side deployment via llama.cpp, vLLM, or Transformers.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 24.3 GB | 27.5 GB | Too big | Get file → | |
| Q2_K | 27.3 GB | 30.5 GB | Too big | Get file → | |
| IQ3_XXS | 27.4 GB | 30.6 GB | Too big | Get file → | |
| IQ3_XS | 29.6 GB | 32.8 GB | Too big | Get file → | |
| Q3_K_S | 30.8 GB | 34.0 GB | Too big | Get file → | |
| IQ3_M | 32.0 GB | 35.2 GB | Too big | Get file → | |
| Q3_K_M | 35.5 GB | 38.7 GB | Too big | Get file → | |
| IQ4_XS | 37.9 GB | 41.1 GB | Too big | Get file → | |
| Q3_K_L | 39.6 GB | 42.8 GB | Too big | Get file → | |
| IQ4_NL | 40.1 GB | 43.3 GB | Too big | Get file → | |
| Q4_K_S | 40.4 GB | 43.6 GB | Too big | Get file → | |
| Q4_K_M | 43.7 GB | 46.9 GB | Too big | Get file → | |
| Q5_K_S | 48.7 GB | 51.9 GB | Too big | Get file → | |
| Q5_K_M | 50.6 GB (2 parts) | 53.8 GB | Too big | Get file → | |
| Q6_K | 57.9 GB (2 parts) | 61.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_M (24.27 GB file, 27.5 GB memory at 8k context). For 16 GB VRAM, Q2_K (27.27 GB file, 30.5 GB memory) or IQ3_XXS (27.41 GB file, 30.6 GB memory). For 24 GB VRAM, Q3_K_S (30.77 GB file, 34 GB memory) or IQ4_XS (37.93 GB file, 41.1 GB memory).
What GPU do you need for Apertus 70B Instruct 2509?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is IQ3_XXS (27.4 GB file, about 30.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_M (43.7 GB file, about 46.9 GB in use).
Which Apertus 70B Instruct 2509 quant should you choose?
Q4_K_M is the usual starting point for Apertus 70B Instruct 2509: it balances file size and quality well. Here it is a 43.7 GB file.
If memory is tight, the smallest file is IQ2_M at 24.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Apertus 70B Instruct 2509
How much VRAM does Apertus 70B Instruct 2509 need?
About 46.9 GB at Q4_K_M with an 8K context window. That is the 43.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Apertus 70B Instruct 2509 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 27.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Apertus 70B Instruct 2509 GGUF?
It depends on the quant: IQ2_M is 24.3 GB, Q2_K is 27.3 GB, IQ3_XXS is 27.4 GB, IQ3_XS is 29.6 GB, Q3_K_S is 30.8 GB, IQ3_M is 32.0 GB and 9 more.
What context length does Apertus 70B Instruct 2509 support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download Apertus 70B Instruct 2509 GGUF?
The files are on Hugging Face in the redponike/Apertus-70B-Instruct-2509-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Apertus 70B Instruct 2509 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Apertus 70B Instruct 2509 on 8 GB VRAM?
Use the IQ2_M quant, which requires 27.5 GB memory at 8k context, so 8 GB VRAM is insufficient for full inference.
Does the model support image inputs?
No, Apertus 70B Instruct 2509 does not support vision.
What is the maximum context length?
The model supports up to 65,536 tokens.