ET

Etheria 55b v0.1 i1

EtheriaGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters55.6B
Context195K
Layers98
Architecturellama
Smallest quant12.6 GB
Quick answer

Etheria 55b v0.1 i1 needs about 37.7 GB of memory at Q4_K_M (a 33.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 19 quants, from 12.6 GB (IQ1_S) to 46.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 13.2 GB.

Etheria 55b v0.1 i1 – 55.6B parameter LLaMA model in GGUF format

Etheria 55b v0.1 i1 is a 55.6B parameter LLaMA model quantized into GGUF files. It supports a trained context of 200000 tokens and is released under the apache-2.0 license. The model is available in multiple quantizations ranging from IQ1_S to Q6_K.

Good at

  • Large context handling
  • High parameter count
  • Flexible quantization options

Limits

  • No vision support
  • Requires significant VRAM for higher quants
  • Context length may be limited to 32k in practice

Best for

  • Research prototyping
  • High‑capacity text generation
  • Fine‑tuning on large corpora

Who it’s for. Developers and researchers who need a large LLaMA model with flexible quantization. The model is suitable for those who can allocate sufficient GPU memory and are comfortable configuring GGUF files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S12.6 GB 16.4 GB
Too big Get file →
IQ2_XXS15.5 GB 19.3 GB
Too big Get file →
IQ2_XS17.1 GB 20.9 GB
Too big Get file →
IQ2_S18.1 GB 21.9 GB
Too big Get file →
IQ2_M19.6 GB 23.3 GB
Too big Get file →
Q2_K21.2 GB 24.9 GB
Too big Get file →
IQ3_XXS22.1 GB 25.8 GB
Too big Get file →
IQ3_XS23.3 GB 27.1 GB
Too big Get file →
Q3_K_S24.6 GB 28.4 GB
Too big Get file →
IQ3_S24.7 GB 28.5 GB
Too big Get file →
IQ3_M25.6 GB 29.4 GB
Too big Get file →
Q3_K_M27.4 GB 31.2 GB
Too big Get file →
Q3_K_L29.8 GB 33.6 GB
Too big Get file →
IQ4_XS30.3 GB 34.1 GB
Too big Get file →
Q4_K_S32.2 GB 35.9 GB
Too big Get file →
Q4_K_M33.9 GB 37.7 GB
Too big Get file →
Q5_K_S38.8 GB 42.6 GB
Too big Get file →
Q5_K_M39.8 GB 43.6 GB
Too big Get file →
Q6_K46.1 GB 49.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 12.57 GB, estimated 16.4 GB memory). For 12 GB VRAM, IQ2_XXS (15.51 GB, 19.3 GB memory). For 16 GB VRAM, IQ2_XS (17.14 GB, 20.9 GB memory). Higher quants require proportionally more VRAM.

What GPU do you need for Etheria 55b v0.1 i1?

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 IQ2_M (19.6 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_M (27.4 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_M (39.8 GB file, about 43.6 GB in use).

Which Etheria 55b v0.1 i1 quant should you choose?

Q4_K_M is the usual starting point for Etheria 55b v0.1 i1: it balances file size and quality well. Here it is a 33.9 GB file.

If memory is tight, the smallest file is IQ1_S at 12.6 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
Parameters55.6B
Layers98
Trained context200,000 tokens
KV cache (fp16)392 KB per token

Source

Quantized bymradermacher
FamilyEtheria
Licenseapache-2.0
Downloads (HF)572
Last updated2024-12-16

Frequently asked questions about Etheria 55b v0.1 i1

How much VRAM does Etheria 55b v0.1 i1 need?

About 37.7 GB at Q4_K_M with an 8K context window. That is the 33.9 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 Etheria 55b v0.1 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Etheria 55b v0.1 i1 GGUF?

It depends on the quant: IQ1_S is 12.6 GB, IQ2_XXS is 15.5 GB, IQ2_XS is 17.1 GB, IQ2_S is 18.1 GB, IQ2_M is 19.6 GB, Q2_K is 21.2 GB and 13 more.

What context length does Etheria 55b v0.1 i1 support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 3.3 GB at 8K and 13.2 GB at 32K.

Where can I download Etheria 55b v0.1 i1 GGUF?

The files are on Hugging Face in the mradermacher/Etheria-55b-v0.1-i1-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 Etheria 55b v0.1 i1 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.

Can I run this model on 8 GB VRAM?

Use the IQ1_S quant, which estimates 16.4 GB memory at 8k context. 8 GB VRAM will be insufficient for full inference.

What is the maximum context length I can use?

The model was trained with 200000 tokens, but practical usage is recommended up to 32k tokens due to merge uncertainties.

Is this model licensed for commercial use?

Yes, it is released under the apache-2.0 license, which permits commercial use.

Other GGUFs of Etheria-55b-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Etheria models

All Etheria →

Other large models

All large models →