DU

Dusk-Miqu-70B

DuskGGUF by mradermacherUpdated 2024-05-19
Download on Hugging Face
Parameters69B
Context32K
Layers80
Architecturellama
Smallest quant25.5 GB
Quick answer

Dusk-Miqu-70B 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 12 quants, from 25.5 GB (Q2_K) to 48.8 GB (Q5_K_M).

Dusk-Miqu-70B – a 70B dark fantasy LLaMA model

Dusk-Miqu-70B is a 69‑billion‑parameter LLaMA model with a 32,764‑token context window. It is a dark‑creative writing model that excels at grimdark fantasy. The model is available in multiple GGUF quantizations.

Good at

  • Grimdark fantasy writing
  • Dark creative storytelling
  • Vicuna prompt format

Limits

  • No vision support
  • Non‑commercial use only
  • Large VRAM requirement for higher quants

Best for

  • Writing dark fantasy novels
  • Generating grimdark short stories
  • Creative writing prompts

Who it’s for. Developers and writers who need a large language model specialized in dark fantasy content. The model is suitable for personal, non‑commercial projects.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.5 GB 28.6 GB
Too big Get file →
IQ3_XS28.3 GB 31.5 GB
Too big Get file →
IQ3_S29.9 GB 33.1 GB
Too big Get file →
Q3_K_S29.9 GB 33.1 GB
Too big Get file →
IQ3_M30.9 GB 34.1 GB
Too big Get file →
Q3_K_M33.3 GB 36.5 GB
Too big Get file →
Q3_K_L36.1 GB 39.3 GB
Too big Get file →
IQ4_XS37.2 GB 40.4 GB
Too big Get file →
Q4_K_S39.2 GB 42.4 GB
Too big Get file →
Q4_K_M41.4 GB 44.6 GB
Too big Get file →
Q5_K_S47.5 GB 50.6 GB
Too big Get file →
Q5_K_M48.8 GB 51.9 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (25.46 GB, 28.6 GB memory at 8k context) or IQ3_XS (28.31 GB, 31.5 GB memory). For 16 GB VRAM, Q4_K_S (39.25 GB, 42.4 GB memory) or Q5_K_S (47.46 GB, 50.6 GB memory) are recommended. Memory estimates are approximate.

What GPU do you need for Dusk-Miqu-70B?

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_XS (28.3 GB file, about 31.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which Dusk-Miqu-70B quant should you choose?

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

If memory is tight, the smallest file is Q2_K at 25.5 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

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

Source

Quantized bymradermacher
FamilyDusk
Licenseother
Downloads (HF)767
Last updated2024-05-19

Frequently asked questions about Dusk-Miqu-70B

How much VRAM does Dusk-Miqu-70B 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 Dusk-Miqu-70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Dusk-Miqu-70B GGUF?

It depends on the quant: Q2_K is 25.5 GB, IQ3_XS is 28.3 GB, IQ3_S is 29.9 GB, Q3_K_S is 29.9 GB, IQ3_M is 30.9 GB, Q3_K_M is 33.3 GB and 6 more.

What context length does Dusk-Miqu-70B 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 Dusk-Miqu-70B GGUF?

The files are on Hugging Face in the mradermacher/Dusk-Miqu-70B-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 Dusk-Miqu-70B 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.

Can I run Dusk-Miqu-70B on 8 GB VRAM?

Only the lowest quants such as Q2_K or IQ3_XS may fit, but they still require around 28–31 GB of VRAM at 8k context. 8 GB is insufficient.

Is Dusk-Miqu-70B suitable for commercial use?

No. The model is licensed for non‑commercial, personal use only.

Does the model support vision tasks?

No. The model has no vision capabilities.

Other GGUFs of Dusk-Miqu-70B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Dusk models

All Dusk →

Other large models

All large models →