MI

MN Miuryra 18B Q3 K M

MiuryraGGUF by djunaUpdated 2024-10-17
Download on Hugging Face
Parameters18.2B
Context1000K
Layers62
Architecturellama
Smallest quant9.0 GB
Quick answer

MN Miuryra 18B Q3 K M needs about 11.5 GB of memory at Q3_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.

MN Miuryra 18B Q3 K M is a 18.2B-parameter Miuryra model in GGUF format, quantized by djuna. Its trained context length is 1000K tokens. The repository has 1 quant file, from 9.0 GB (Q3_K_M) to 9.0 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M9.0 GB 11.5 GB
Too big Get file →

What GPU do you need for MN Miuryra 18B Q3 K M?

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: the best quant that fits is Q3_K_M (9.0 GB file, about 11.5 GB in use).

Which MN Miuryra 18B Q3 K M quant should you choose?

Q3_K_M (9.0 GB) is the middle option in this repository. 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
Parameters18.2B
Layers62
Trained context1,024,000 tokens
KV cache (fp16)248 KB per token

Source

Quantized bydjuna
FamilyMiuryra
Downloads (HF)7
Last updated2024-10-17

Frequently asked questions about MN Miuryra 18B Q3 K M

How much VRAM does MN Miuryra 18B Q3 K M need?

About 11.5 GB at Q3_K_M with an 8K context window. That is the 9.0 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 MN Miuryra 18B Q3 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MN Miuryra 18B Q3 K M GGUF?

It depends on the quant: Q3_K_M is 9.0 GB.

What context length does MN Miuryra 18B Q3 K M support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.3 GB at 32K.

Where can I download MN Miuryra 18B Q3 K M GGUF?

The files are on Hugging Face in the djuna/MN-Miuryra-18B-Q3_K_M-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of MN-Miuryra-18B

Similar models

Browse all →

More from djuna

All by djuna →

More Miuryra models

All Miuryra →

Other medium models

All medium models →