MI

Midnight Miqu 103B v1.5 i1

MidnightGGUF by mradermacherUpdated 2024-05-14
Download on Hugging Face
Parameters103B
Context32K
Layers120
Architecturellama
Smallest quant22.0 GB
Quick answer

Midnight Miqu 103B v1.5 i1 needs about 39.6 GB of memory at IQ2_M (a 35.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 22.0 GB (IQ1_S) to 46.4 GB (IQ3_M).

Midnight Miqu 103B v1.5 i1 – a 103B LLaMA model with 32K context

Midnight Miqu 103B v1.5 i1 is a 103B parameter LLaMA model merged from Midnight-Miqu-70B-v1.5. It supports a 32764 token context window. The model is available in multiple GGUF quantizations.

Good at

  • Large context reasoning
  • High parameter count
  • LLM inference with GGUF

Limits

  • No license for commercial use
  • No vision support
  • Requires large VRAM for full precision

Best for

  • Research prototypes
  • Personal LLM projects
  • Custom fine‑tuning

Who it’s for. Developers and researchers who need a large LLaMA model for personal use and are comfortable managing legal and memory constraints. The model is not intended for commercial deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S22.0 GB 26.5 GB
Too big Get file →
IQ1_M23.8 GB 28.3 GB
Too big Get file →
IQ2_XXS27.6 GB 32.2 GB
Too big Get file →
IQ2_XS30.7 GB 35.2 GB
Too big Get file →
IQ2_S32.2 GB 36.8 GB
Too big Get file →
IQ2_M35.0 GB 39.6 GB
Too big Get file →
Q2_K38.2 GB 42.8 GB
Too big Get file →
IQ3_XXS39.9 GB 44.5 GB
Too big Get file →
IQ3_XS42.4 GB 46.9 GB
Too big Get file →
Q3_K_S44.8 GB 49.3 GB
Too big Get file →
IQ3_S44.9 GB 49.4 GB
Too big Get file →
IQ3_M46.4 GB 51.0 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (22.01 GB file, 26.5 GB memory at 8 k context). For 12 GB VRAM use IQ1_M (23.78 GB file, 28.3 GB memory). For 16 GB VRAM use IQ2_S (32.23 GB file, 36.8 GB memory). Estimates are approximate.

What GPU do you need for Midnight Miqu 103B v1.5 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: the best quant that fits is IQ1_M (23.8 GB file, about 28.3 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ3_XS (42.4 GB file, about 46.9 GB in use).

Which Midnight Miqu 103B v1.5 i1 quant should you choose?

IQ2_M (35.0 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 IQ1_S at 22.0 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

Architecturellama
Parameters103B
Layers120
Trained context32,764 tokens
KV cache (fp16)480 KB per token

Source

Quantized bymradermacher
FamilyMidnight
Downloads (HF)1,599
Last updated2024-05-14

Frequently asked questions about Midnight Miqu 103B v1.5 i1

How much VRAM does Midnight Miqu 103B v1.5 i1 need?

About 39.6 GB at IQ2_M with an 8K context window. That is the 35.0 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 103B v1.5 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 26.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Midnight Miqu 103B v1.5 i1 GGUF?

It depends on the quant: IQ1_S is 22.0 GB, IQ1_M is 23.8 GB, IQ2_XXS is 27.6 GB, IQ2_XS is 30.7 GB, IQ2_S is 32.2 GB, IQ2_M is 35.0 GB and 6 more.

What context length does Midnight Miqu 103B v1.5 i1 support?

The GGUF header lists a trained context length of 32,764 tokens (32K). The KV cache grows with the context you use: about 4.0 GB at 8K and 16.1 GB at 32K.

Where can I download Midnight Miqu 103B v1.5 i1 GGUF?

The files are on Hugging Face in the mradermacher/Midnight-Miqu-103B-v1.5-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Use the IQ1_S quant, which requires about 26.5 GB of VRAM at 8 k context, so 8 GB VRAM is insufficient.

Is this model suitable for commercial use?

No. The model is only suitable for personal use and has no commercial license.

What context length does this model support?

The model supports a 32764 token context window.

Other GGUFs of Midnight-Miqu-103B-v1.5

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Midnight models

All Midnight →

Other large models

All large models →