ME

Merak 7B v5 PROTOTYPE1

MerakGGUF by Ichsan2895Updated 2023-12-14
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.1 GB
Quick answer

Merak 7B v5 PROTOTYPE1 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 8 quants, from 3.1 GB (Q2_K) to 7.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Merak 7B v5 PROTOTYPE1 is a 7.24B-parameter Merak model in GGUF format, quantized by Ichsan2895. Its trained context length is 32K tokens. The repository has 8 quant files, from 3.1 GB (Q2_K) to 7.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 4.7 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_05.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →

What GPU do you need for Merak 7B v5 PROTOTYPE1?

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: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which Merak 7B v5 PROTOTYPE1 quant should you choose?

Q4_K_M is the usual starting point for Merak 7B v5 PROTOTYPE1: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 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 3.1 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byIchsan2895
FamilyMerak
Downloads (HF)211
Last updated2023-12-14

Frequently asked questions about Merak 7B v5 PROTOTYPE1

How much VRAM does Merak 7B v5 PROTOTYPE1 need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 Merak 7B v5 PROTOTYPE1 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Merak 7B v5 PROTOTYPE1 GGUF?

It depends on the quant: Q2_K is 3.1 GB, Q3_K_M is 3.5 GB, Q4_0 is 4.1 GB, Q4_K_M is 4.4 GB, Q5_0 is 5.0 GB, Q5_K_M is 5.1 GB and 2 more.

What context length does Merak 7B v5 PROTOTYPE1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Merak 7B v5 PROTOTYPE1 GGUF?

The files are on Hugging Face in the Ichsan2895/Merak-7B-v5-PROTOTYPE1-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 Merak 7B v5 PROTOTYPE1 use?

Hugging Face lists the license as cc-by-nc-sa-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from Ichsan2895

All by Ichsan2895 →

More Merak models

All Merak →

Other small models

All small models →