ME

Medorca 2x7b

MedorcaGGUF by LoneStrikerUpdated 2024-01-22
Download on Hugging Face
Parameters11.1B
Context4K
Layers32
Architecturellama
Smallest quant4.8 GB
Quick answer

Medorca 2x7b needs about 11.5 GB of memory at Q4_K_M (a 6.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 9 quants, from 4.8 GB (Q3_K_S) to 11.8 GB (Q8_0).

Medorca 2x7b is a 11.1B-parameter Medorca model in GGUF format, quantized by LoneStriker. Its trained context length is 4K tokens. The repository has 9 quant files, from 4.8 GB (Q3_K_S) to 11.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S4.8 GB 7.5 GB
Tight Get file →
Q3_K_M5.4 GB 8.0 GB
Too big Get file →
Q3_K_L5.8 GB 8.5 GB
Too big Get file →
Q4_K_S6.3 GB 9.0 GB
Too big Get file →
Q4_K_M6.7 GB 9.3 GB
Too big Get file →
Q5_K_S7.6 GB 10.3 GB
Too big Get file →
Q5_K_M7.9 GB 10.5 GB
Too big Get file →
Q6_K9.1 GB 11.7 GB
Too big Get file →
Q8_011.8 GB 14.4 GB
Too big Get file →

What GPU do you need for Medorca 2x7b?

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 Q4_K_M (6.7 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (9.1 GB file, about 13.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (11.8 GB file, about 16.6 GB in use).

Which Medorca 2x7b quant should you choose?

Q4_K_M is the usual starting point for Medorca 2x7b: it balances file size and quality well. Here it is a 6.7 GB file.

The Q8_0 file is 11.8 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 Q3_K_S at 4.8 GB, with the quality trade-offs that come with fewer bits. 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
Parameters11.1B (approximate, mixture of experts)
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byLoneStriker
FamilyMedorca
Licenseapache-2.0
Downloads (HF)84
Last updated2024-01-22

Frequently asked questions about Medorca 2x7b

How much VRAM does Medorca 2x7b need?

About 11.5 GB at Q4_K_M with an 8K context window. That is the 6.7 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 Medorca 2x7b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Medorca 2x7b GGUF?

It depends on the quant: Q3_K_S is 4.8 GB, Q3_K_M is 5.4 GB, Q3_K_L is 5.8 GB, Q4_K_S is 6.3 GB, Q4_K_M is 6.7 GB, Q5_K_S is 7.6 GB and 3 more.

What context length does Medorca 2x7b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Medorca 2x7b GGUF?

The files are on Hugging Face in the LoneStriker/Medorca-2x7b-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 Medorca 2x7b use?

Hugging Face lists the license as apache-2.0. 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 LoneStriker

All by LoneStriker →

More Medorca models

All Medorca →

Other medium models

All medium models →