EM

Emerhyst 2x20B Base

EmerhystGGUF by mradermacherUpdated 2024-11-20
Download on Hugging Face
Parameters33.2B
Context4K
Layers62
Architecturellama
Smallest quant12.2 GB
Quick answer

Emerhyst 2x20B Base needs about 30.9 GB of memory at Q4_K_M (a 20.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 11 quants, from 12.2 GB (Q2_K) to 35.2 GB (Q8_0).

Emerhyst 2x20B Base is a 33.2B-parameter Emerhyst model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 11 quant files, from 12.2 GB (Q2_K) to 35.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.2 GB 17.9 GB
Too big Get file →
Q3_K_S14.3 GB 20.0 GB
Too big Get file →
Q3_K_M16.0 GB 21.7 GB
Too big Get file →
Q3_K_L17.4 GB 23.1 GB
Too big Get file →
IQ4_XS17.8 GB 23.5 GB
Too big Get file →
Q4_K_S18.8 GB 24.5 GB
Too big Get file →
Q4_K_M20.0 GB 25.7 GB
Too big Get file →
Q5_K_S22.8 GB 28.5 GB
Too big Get file →
Q5_K_M23.5 GB 29.2 GB
Too big Get file →
Q6_K27.2 GB 32.9 GB
Too big Get file →
Q8_035.2 GB 40.9 GB
Too big Get file →

What GPU do you need for Emerhyst 2x20B Base?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q2_K (12.2 GB file, about 23.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (20.0 GB file, about 30.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (35.2 GB file, about 46.1 GB in use).

Which Emerhyst 2x20B Base quant should you choose?

Q4_K_M is the usual starting point for Emerhyst 2x20B Base: it balances file size and quality well. Here it is a 20.0 GB file.

The Q8_0 file is 35.2 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 12.2 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
Parameters33.2B (approximate, mixture of experts)
Layers62
Trained context4,096 tokens
KV cache (fp16)1240 KB per token

Source

Quantized bymradermacher
FamilyEmerhyst
Downloads (HF)67
Last updated2024-11-20

Frequently asked questions about Emerhyst 2x20B Base

How much VRAM does Emerhyst 2x20B Base need?

About 30.9 GB at Q4_K_M with an 8K context window. That is the 20.0 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 Emerhyst 2x20B Base on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Emerhyst 2x20B Base GGUF?

It depends on the quant: Q2_K is 12.2 GB, Q3_K_S is 14.3 GB, Q3_K_M is 16.0 GB, Q3_K_L is 17.4 GB, IQ4_XS is 17.8 GB, Q4_K_S is 18.8 GB and 5 more.

What context length does Emerhyst 2x20B Base support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 10.4 GB at 8K and 5.2 GB at 4K.

Where can I download Emerhyst 2x20B Base GGUF?

The files are on Hugging Face in the mradermacher/Emerhyst-2x20B-Base-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 mradermacher

All by mradermacher →

More Emerhyst models

All Emerhyst →

Other medium models

All medium models →