MultiVerse 70B i1 needs about 67.2 GB of memory at Q4_K_M (a 45.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 18 quants, from 17.9 GB (IQ1_S) to 45.2 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 85.9 GB.
MultiVerse 70B i1 is a 72.3B-parameter Multiverse model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 18 quant files, from 17.9 GB (IQ1_S) to 45.2 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 17.9 GB | 39.8 GB | Too big | Get file → | |
| IQ1_M | 19.2 GB | 41.2 GB | Too big | Get file → | |
| IQ2_XXS | 21.4 GB | 43.4 GB | Too big | Get file → | |
| IQ2_XS | 23.4 GB | 45.4 GB | Too big | Get file → | |
| IQ2_S | 25.0 GB | 47.0 GB | Too big | Get file → | |
| IQ2_M | 26.8 GB | 48.8 GB | Too big | Get file → | |
| Q2_K | 28.5 GB | 50.5 GB | Too big | Get file → | |
| IQ3_XXS | 29.3 GB | 51.3 GB | Too big | Get file → | |
| IQ3_XS | 31.4 GB | 53.4 GB | Too big | Get file → | |
| IQ3_S | 33.0 GB | 55.0 GB | Too big | Get file → | |
| Q3_K_S | 33.0 GB | 55.0 GB | Too big | Get file → | |
| IQ3_M | 34.7 GB | 56.7 GB | Too big | Get file → | |
| Q3_K_M | 36.7 GB | 58.7 GB | Too big | Get file → | |
| Q3_K_L | 40.0 GB | 61.9 GB | Too big | Get file → | |
| IQ4_XS | 40.3 GB | 62.2 GB | Too big | Get file → | |
| Q4_0 | 42.6 GB | 64.6 GB | Too big | Get file → | |
| Q4_K_S | 42.8 GB | 64.7 GB | Too big | Get file → | |
| Q4_K_M | 45.2 GB | 67.2 GB | Too big | Get file → |
What GPU do you need for MultiVerse 70B i1?
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 IQ2_S (25.0 GB file, about 47.0 GB in use).
Which MultiVerse 70B i1 quant should you choose?
Q4_K_M is the usual starting point for MultiVerse 70B i1: it balances file size and quality well. Here it is a 45.2 GB file.
If memory is tight, the smallest file is IQ1_S at 17.9 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 MultiVerse 70B i1
How much VRAM does MultiVerse 70B i1 need?
About 67.2 GB at Q4_K_M with an 8K context window. That is the 45.2 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 MultiVerse 70B i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 39.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MultiVerse 70B i1 GGUF?
It depends on the quant: IQ1_S is 17.9 GB, IQ1_M is 19.2 GB, IQ2_XXS is 21.4 GB, IQ2_XS is 23.4 GB, IQ2_S is 25.0 GB, IQ2_M is 26.8 GB and 12 more.
What context length does MultiVerse 70B i1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 21.5 GB at 8K and 85.9 GB at 32K.
Where can I download MultiVerse 70B i1 GGUF?
The files are on Hugging Face in the mradermacher/MultiVerse_70B-i1-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 MultiVerse 70B i1 use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.