MiquMaid v2 2x70B DPO needs about 45.8 GB of memory at Q2_K_S (a 42.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 5 quants, from 33.0 GB (IQ2_XXS) to 48.6 GB (IQ3_XXS).
MiquMaid v2 2x70B DPO is a 125B-parameter Miqumaid model in GGUF format, quantized by NeverSleep. Its trained context length is 32K tokens. The repository has 5 quant files, from 33.0 GB (IQ2_XXS) to 48.6 GB (IQ3_XXS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 33.0 GB | 36.2 GB | Too big | Get file → | |
| IQ2_XS | 36.7 GB | 39.9 GB | Too big | Get file → | |
| Q2_K_S | 42.6 GB | 45.8 GB | Too big | Get file → | |
| Q2_K | 45.9 GB | 49.1 GB | Too big | Get file → | |
| IQ3_XXS | 48.6 GB | 51.8 GB | Too big | Get file → |
What GPU do you need for MiquMaid v2 2x70B DPO?
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 Q2_K_S (42.6 GB file, about 45.8 GB in use).
Which MiquMaid v2 2x70B DPO quant should you choose?
Q2_K_S (42.6 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ2_XXS at 33.0 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 MiquMaid v2 2x70B DPO
How much VRAM does MiquMaid v2 2x70B DPO need?
About 45.8 GB at Q2_K_S with an 8K context window. That is the 42.6 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 MiquMaid v2 2x70B DPO on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 36.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MiquMaid v2 2x70B DPO GGUF?
It depends on the quant: IQ2_XXS is 33.0 GB, IQ2_XS is 36.7 GB, Q2_K_S is 42.6 GB, Q2_K is 45.9 GB, IQ3_XXS is 48.6 GB.
What context length does MiquMaid v2 2x70B DPO support?
The GGUF header lists a trained context length of 32,764 tokens (32K). 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 MiquMaid v2 2x70B DPO GGUF?
The files are on Hugging Face in the NeverSleep/MiquMaid-v2-2x70B-DPO-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 MiquMaid v2 2x70B DPO use?
Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.