KA

Karakuri Midroze Mg

KarakuriGGUF by mradermacherUpdated 2024-11-30
Download on Hugging Face
Parameters69.2B
Context4K
Layers80
Architecturellama
Smallest quant25.6 GB
Quick answer

Karakuri Midroze Mg needs about 44.8 GB of memory at Q4_K_M (a 41.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 9 quants, from 25.6 GB (Q2_K) to 48.9 GB (Q5_K_M).

Karakuri Midroze Mg is a 69.2B-parameter Karakuri model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 9 quant files, from 25.6 GB (Q2_K) to 48.9 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.6 GB 27.4 GB
Too big Get file →
Q3_K_S30.1 GB 31.9 GB
Too big Get file →
Q3_K_M33.4 GB 35.3 GB
Too big Get file →
Q3_K_L36.3 GB 38.1 GB
Too big Get file →
IQ4_XS37.3 GB 39.2 GB
Too big Get file →
Q4_K_S39.4 GB 41.2 GB
Too big Get file →
Q4_K_M41.6 GB 43.4 GB
Too big Get file →
Q5_K_S47.6 GB 49.5 GB
Too big Get file →
Q5_K_M48.9 GB 50.8 GB
Too big Get file →

What GPU do you need for Karakuri Midroze Mg?

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 Q2_K (25.6 GB file, about 28.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.6 GB file, about 44.8 GB in use).

Which Karakuri Midroze Mg quant should you choose?

Q4_K_M is the usual starting point for Karakuri Midroze Mg: it balances file size and quality well. Here it is a 41.6 GB file.

If memory is tight, the smallest file is Q2_K at 25.6 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
Parameters69.2B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyKarakuri
Downloads (HF)174
Last updated2024-11-30

Frequently asked questions about Karakuri Midroze Mg

How much VRAM does Karakuri Midroze Mg need?

About 44.8 GB at Q4_K_M with an 8K context window. That is the 41.6 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 Karakuri Midroze Mg on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Karakuri Midroze Mg GGUF?

It depends on the quant: Q2_K is 25.6 GB, Q3_K_S is 30.1 GB, Q3_K_M is 33.4 GB, Q3_K_L is 36.3 GB, IQ4_XS is 37.3 GB, Q4_K_S is 39.4 GB and 3 more.

What context length does Karakuri Midroze Mg support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download Karakuri Midroze Mg GGUF?

The files are on Hugging Face in the mradermacher/karakuri-midroze-mg-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Karakuri models

All Karakuri →

Other large models

All large models →