TE

Technoculture Medorca 4x7b

TechnocultureGGUF by RichardErkhovUpdated 2024-05-12
Download on Hugging Face
Parameters19.7B
Context4K
Layers32
Architecturellama
Smallest quant7.2 GB
Quick answer

Technoculture Medorca 4x7b needs about 16.7 GB of memory at Q4_K_M (a 11.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 7.2 GB (Q2_K) to 16.2 GB (Q6_K).

Technoculture Medorca 4x7b is a 19.7B-parameter Technoculture model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 21 quant files, from 7.2 GB (Q2_K) to 16.2 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K7.2 GB 9.9 GB
Too big Get file →
IQ3_XS8.1 GB 10.7 GB
Too big Get file →
IQ3_S8.5 GB 11.2 GB
Too big Get file →
Q3_K_S8.5 GB 11.2 GB
Too big Get file →
IQ3_M8.8 GB 11.4 GB
Too big Get file →
Q3_K9.5 GB 12.1 GB
Too big Get file →
Q3_K_M9.5 GB 12.1 GB
Too big Get file →
Q3_K_L10.3 GB 12.9 GB
Too big Get file →
IQ4_XS10.6 GB 13.3 GB
Too big Get file →
Q4_011.1 GB 13.8 GB
Too big Get file →
IQ4_NL11.2 GB 13.9 GB
Too big Get file →
Q4_K_S11.2 GB 13.9 GB
Too big Get file →
Q4_K11.9 GB 14.6 GB
Too big Get file →
Q4_K_M11.9 GB 14.6 GB
Too big Get file →
Q4_112.4 GB 15.0 GB
Too big Get file →
Q5_013.6 GB 16.2 GB
Too big Get file →
Q5_K_S13.6 GB 16.2 GB
Too big Get file →
Q5_K14.0 GB 16.6 GB
Too big Get file →
Q5_K_M14.0 GB 16.6 GB
Too big Get file →
Q5_114.8 GB 17.5 GB
Too big Get file →
Q6_K16.2 GB 18.8 GB
Too big Get file →

What GPU do you need for Technoculture Medorca 4x7b?

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 Q2_K (7.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (11.2 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (16.2 GB file, about 21.0 GB in use).

Which Technoculture Medorca 4x7b quant should you choose?

Q4_K_M is the usual starting point for Technoculture Medorca 4x7b: it balances file size and quality well. Here it is a 11.9 GB file.

If memory is tight, the smallest file is Q2_K at 7.2 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
Parameters19.7B (approximate, mixture of experts)
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byRichardErkhov
Downloads (HF)11
Last updated2024-05-12

Frequently asked questions about Technoculture Medorca 4x7b

How much VRAM does Technoculture Medorca 4x7b need?

About 16.7 GB at Q4_K_M with an 8K context window. That is the 11.9 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 Technoculture Medorca 4x7b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Technoculture Medorca 4x7b GGUF?

It depends on the quant: Q2_K is 7.2 GB, IQ3_XS is 8.1 GB, IQ3_S is 8.5 GB, Q3_K_S is 8.5 GB, IQ3_M is 8.8 GB, Q3_K is 9.5 GB and 15 more.

What context length does Technoculture Medorca 4x7b 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 Technoculture Medorca 4x7b GGUF?

The files are on Hugging Face in the RichardErkhov/Technoculture_-_Medorca-4x7b-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 RichardErkhov

All by RichardErkhov →

More Technoculture models

All Technoculture →

Other medium models

All medium models →