MI

MiquMaid-v2-70B-DPO

MiqumaidGGUF by NeverSleepUpdated 2024-02-07
Download on Hugging Face
Parameters69B
Context32K
Layers80
Architecturellama
Smallest quant33.3 GB
Quick answer

MiquMaid-v2-70B-DPO needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 5 quants, from 33.3 GB (Q3_K_M) to 48.8 GB (Q5_K_M).

MiquMaid-v2-70B-DPO is a 69B-parameter Miqumaid model in GGUF format, quantized by NeverSleep. Its trained context length is 32K tokens. The repository has 5 quant files, from 33.3 GB (Q3_K_M) to 48.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M33.3 GB 36.5 GB
Too big Get file →
Q4_038.9 GB 42.1 GB
Too big Get file →
Q4_K_M41.4 GB 44.6 GB
Too big Get file →
Q5_047.5 GB 50.6 GB
Too big Get file →
Q5_K_M48.8 GB 51.9 GB
Too big Get file →

What GPU do you need for MiquMaid-v2-70B-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 Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which MiquMaid-v2-70B-DPO quant should you choose?

Q4_K_M is the usual starting point for MiquMaid-v2-70B-DPO: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q3_K_M at 33.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters69B
Layers80
Trained context32,764 tokens
KV cache (fp16)320 KB per token

Source

Quantized byNeverSleep
FamilyMiqumaid
Downloads (HF)14
Last updated2024-02-07

Frequently asked questions about MiquMaid-v2-70B-DPO

How much VRAM does MiquMaid-v2-70B-DPO need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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-v2-70B-DPO on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 36.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MiquMaid-v2-70B-DPO GGUF?

It depends on the quant: Q3_K_M is 33.3 GB, Q4_0 is 38.9 GB, Q4_K_M is 41.4 GB, Q5_0 is 47.5 GB, Q5_K_M is 48.8 GB.

What context length does MiquMaid-v2-70B-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-v2-70B-DPO GGUF?

The files are on Hugging Face in the NeverSleep/MiquMaid-v2-70B-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-v2-70B-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.

Similar models

Browse all →

More from NeverSleep

All by NeverSleep →

More Miqumaid models

All Miqumaid →

Other large models

All large models →