Apertus v1.5 70B text 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. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Apertus v1.5 70B text-only GGUF model
Apertus v1.5 70B is a 70.6B parameter text-only model converted to GGUF. It supports reasoning and tool usage. The conversion is a test quant with no vision or audio towers.
Good at
- reasoning
- tools
- text generation
Limits
- text-only, no vision or audio
- requires --override-kv and -sp flags
- large memory footprint
Best for
- research prototyping
- tool integration
- text analysis
Who it’s for. Developers and researchers who need a large language model for text tasks and are comfortable with test quant files. The model is suitable for those who can manage the required memory and command line flags.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 43.7 GB | 46.9 GB | Too big | Get file → |
The only available quant is Q4_K_M, file size 43.72 GB. Estimated memory usage is 46.9 GB at 8 k context. Use this quant if you have a GPU with at least 48 GB VRAM; otherwise the model will not fit.
What GPU do you need for Apertus v1.5 70B text?
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: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q4_K_M (43.7 GB file, about 46.9 GB in use).
Which Apertus v1.5 70B text quant should you choose?
Q4_K_M is the usual starting point for Apertus v1.5 70B text: it balances file size and quality well. Here it is a 43.7 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Apertus v1.5 70B text
How much VRAM does Apertus v1.5 70B text 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 v1.5 70B text on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 46.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Apertus v1.5 70B text GGUF?
It depends on the quant: Q4_K_M is 43.7 GB.
What context length does Apertus v1.5 70B text support?
The GGUF header lists a trained context length of 262,144 tokens (256K). 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 v1.5 70B text GGUF?
The files are on Hugging Face in the katya228/Apertus-v1.5-70B-text-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 v1.5 70B text 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 this model on 8 GB VRAM?
No, the model requires approximately 46.9 GB of VRAM at 8 k context.
Does this model support image input?
No, the vision tower was stripped; it is text-only.
What flags are required to run the model?
You must use --override-kv tokenizer.ggml.eos_token_id=int:68 and -sp when launching.