MI

Miqu 70b 12

MiquGGUF by mradermacherUpdated 2024-11-04
Download on Hugging Face
Parameters14.2B
Context32K
Layers16
Architecturellama
Smallest quant5.3 GB
Quick answer

Miqu 70b 12 needs about 9.6 GB of memory at Q4_K_M (a 8.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 5.3 GB (Q2_K) to 15.1 GB (Q8_0).

Miqu 70b 12 is a 14.2B-parameter Miqu model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 11 quant files, from 5.3 GB (Q2_K) to 15.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.3 GB 6.4 GB
Fits Get file →
Q3_K_S6.2 GB 7.2 GB
Tight Get file →
Q3_K_M6.9 GB 7.9 GB
Tight Get file →
Q3_K_L7.5 GB 8.5 GB
Too big Get file →
IQ4_XS7.7 GB 8.8 GB
Too big Get file →
Q4_K_S8.1 GB 9.2 GB
Too big Get file →
Q4_K_M8.6 GB 9.6 GB
Too big Get file →
Q5_K_S9.8 GB 10.8 GB
Too big Get file →
Q5_K_M10.1 GB 11.1 GB
Too big Get file →
Q6_K11.7 GB 12.7 GB
Too big Get file →
Q8_015.1 GB 16.1 GB
Too big Get file →

What GPU do you need for Miqu 70b 12?

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: the best quant that fits is Q3_K_M (6.9 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (10.1 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.7 GB file, about 12.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.1 GB file, about 16.1 GB in use).

Which Miqu 70b 12 quant should you choose?

Q4_K_M is the usual starting point for Miqu 70b 12: it balances file size and quality well. Here it is a 8.6 GB file.

The Q8_0 file is 15.1 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 5.3 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
Parameters14.2B
Layers16
Trained context32,764 tokens
KV cache (fp16)64 KB per token

Source

Quantized bymradermacher
FamilyMiqu
Downloads (HF)46
Last updated2024-11-04

Frequently asked questions about Miqu 70b 12

How much VRAM does Miqu 70b 12 need?

About 9.6 GB at Q4_K_M with an 8K context window. That is the 8.6 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 Miqu 70b 12 on an 8 GB GPU?

Yes, with Q3_K_M: the 6.9 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Miqu 70b 12 GGUF?

It depends on the quant: Q2_K is 5.3 GB, Q3_K_S is 6.2 GB, Q3_K_M is 6.9 GB, Q3_K_L is 7.5 GB, IQ4_XS is 7.7 GB, Q4_K_S is 8.1 GB and 5 more.

What context length does Miqu 70b 12 support?

The GGUF header lists a trained context length of 32,764 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.

Where can I download Miqu 70b 12 GGUF?

The files are on Hugging Face in the mradermacher/miqu-70b-12-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 miqu-70b-12

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Miqu models

All Miqu →

Other medium models

All medium models →