MI

Midnight Miqu 70B v1.0

MidnightGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters69B
Context32K
Layers80
Architecturellama
Smallest quant25.8 GB
Quick answer

Midnight Miqu 70B v1.0 needs about 44.9 GB of memory at Q4_K_M (a 41.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 25.8 GB (Q2_K) to 49.1 GB (Q5_K_M).

Midnight Miqu 70B v1.0 – a large LLM for roleplaying and storytelling

Midnight Miqu 70B v1.0 is a 69‑billion‑parameter llama model. It supports up to 32K context with alpha_rope set to 1 and can maintain coherence out to 64K with alpha_rope 2.5. The model is uncensored and designed for creative writing.

Good at

  • Long‑context roleplaying
  • Storytelling
  • Creative text generation

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • Uncensored – user responsibility

Best for

  • Interactive fiction engines
  • Narrative generation tools
  • Creative writing assistants

Who it’s for. Developers and writers who need a large, long‑context model for roleplaying or storytelling. The model is suitable for users who can manage the memory requirements and are comfortable with uncensored content.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.8 GB 29.0 GB
Too big Get file →
IQ3_XS28.5 GB 31.6 GB
Too big Get file →
IQ3_S30.2 GB 33.4 GB
Too big Get file →
Q3_K_S30.2 GB 33.4 GB
Too big Get file →
IQ3_M31.3 GB 34.4 GB
Too big Get file →
Q3_K_M33.6 GB 36.8 GB
Too big Get file →
Q3_K_L36.5 GB 39.6 GB
Too big Get file →
IQ4_XS37.5 GB 40.7 GB
Too big Get file →
Q4_K_S39.6 GB 42.7 GB
Too big Get file →
Q4_K_M41.7 GB 44.9 GB
Too big Get file →
Q5_K_S47.8 GB 51.0 GB
Too big Get file →
Q5_K_M49.1 GB 52.2 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (25.77 GB file, 29 GB memory at 8K context). For 12 GB VRAM, Q3_K_S (30.23 GB file, 33.4 GB memory) is a good balance. For 16 GB VRAM, Q4_K_M (41.73 GB file, 44.9 GB memory) offers higher quality while staying within limits. Estimates are approximate.

What GPU do you need for Midnight Miqu 70B v1.0?

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 (28.5 GB file, about 31.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.7 GB file, about 44.9 GB in use).

Which Midnight Miqu 70B v1.0 quant should you choose?

Q4_K_M is the usual starting point for Midnight Miqu 70B v1.0: it balances file size and quality well. Here it is a 41.7 GB file.

If memory is tight, the smallest file is Q2_K at 25.8 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
FamilyMidnight
Licenseother
Downloads (HF)1,851
Last updated2024-05-06

Frequently asked questions about Midnight Miqu 70B v1.0

How much VRAM does Midnight Miqu 70B v1.0 need?

About 44.9 GB at Q4_K_M with an 8K context window. That is the 41.7 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 Midnight Miqu 70B v1.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Midnight Miqu 70B v1.0 GGUF?

It depends on the quant: Q2_K is 25.8 GB, IQ3_XS is 28.5 GB, IQ3_S is 30.2 GB, Q3_K_S is 30.2 GB, IQ3_M is 31.3 GB, Q3_K_M is 33.6 GB and 6 more.

What context length does Midnight Miqu 70B v1.0 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 Midnight Miqu 70B v1.0 GGUF?

The files are on Hugging Face in the mradermacher/Midnight-Miqu-70B-v1.0-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 Midnight Miqu 70B v1.0 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 Q4_K_M on 12 GB VRAM?

No, Q4_K_M requires about 44.9 GB memory at 8K context, exceeding 12 GB VRAM.

Does this model support image inputs?

No, the model has no vision capabilities.

Is the model censored?

The model is uncensored; users are responsible for its outputs.

Other GGUFs of Midnight-Miqu-70B-v1.0

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Midnight models

All Midnight →

Other large models

All large models →