EU

Euryale 1.3 longLORA 70b rope8 32k fp16 i1

EuryaleGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant14.5 GB
Quick answer

Euryale 1.3 longLORA 70b rope8 32k fp16 i1 needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 20 quants, from 14.5 GB (IQ1_S) to 48.8 GB (Q5_K_M).

Euryale 1.3 longLORA 70b rope8 32k fp16 i1 – 70B Llama model with 32k context

Euryale 1.3 longLORA 70b rope8 32k fp16 i1 is a 69 billion‑parameter Llama model. It supports a 4096‑token trained context and uses linear rope scaling 8 for 32k context capability. The model is released under the llama2 license.

Good at

  • Long‑context text generation
  • Fine‑tuned Llama architecture
  • Large‑scale language modeling

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is llama2

Best for

  • Chatbots needing long context
  • Research on 32k context models
  • Fine‑tuning Llama variants

Who it’s for. Developers and researchers who need a large Llama model with extended context. The model is suitable for those who can manage the memory requirements and are comfortable with GGUF quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S14.5 GB 16.4 GB
Too big Get file →
IQ1_M15.9 GB 17.8 GB
Too big Get file →
IQ2_XXS18.3 GB 20.1 GB
Too big Get file →
IQ2_XS20.3 GB 22.2 GB
Too big Get file →
IQ2_S21.4 GB 23.2 GB
Too big Get file →
IQ2_M23.2 GB 25.1 GB
Too big Get file →
Q2_K25.5 GB 27.3 GB
Too big Get file →
IQ3_XXS26.6 GB 28.4 GB
Too big Get file →
IQ3_XS28.3 GB 30.2 GB
Too big Get file →
IQ3_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
IQ3_M30.9 GB 32.8 GB
Too big Get file →
Q3_K_M33.3 GB 35.1 GB
Too big Get file →
Q3_K_L36.1 GB 38.0 GB
Too big Get file →
IQ4_XS36.8 GB 38.7 GB
Too big Get file →
Q4_039.0 GB 40.9 GB
Too big Get file →
Q4_K_S39.2 GB 41.1 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (file size 14.54 GB, memory 17.7 GB). For 12 GB VRAM use IQ2_S (21.35 GB, 24.5 GB). For 16 GB VRAM use Q4_K_M (41.42 GB, 44.6 GB). Estimates are approximate.

What GPU do you need for Euryale 1.3 longLORA 70b rope8 32k fp16 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_XS (20.3 GB file, about 23.5 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XS (28.3 GB file, about 31.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which Euryale 1.3 longLORA 70b rope8 32k fp16 i1 quant should you choose?

Q4_K_M is the usual starting point for Euryale 1.3 longLORA 70b rope8 32k fp16 i1: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is IQ1_S at 14.5 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyEuryale
Licensellama2
Downloads (HF)2,887
Last updated2024-05-06

Frequently asked questions about Euryale 1.3 longLORA 70b rope8 32k fp16 i1

How much VRAM does Euryale 1.3 longLORA 70b rope8 32k fp16 i1 need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 Euryale 1.3 longLORA 70b rope8 32k fp16 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Euryale 1.3 longLORA 70b rope8 32k fp16 i1 GGUF?

It depends on the quant: IQ1_S is 14.5 GB, IQ1_M is 15.9 GB, IQ2_XXS is 18.3 GB, IQ2_XS is 20.3 GB, IQ2_S is 21.4 GB, IQ2_M is 23.2 GB and 14 more.

What context length does Euryale 1.3 longLORA 70b rope8 32k fp16 i1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download Euryale 1.3 longLORA 70b rope8 32k fp16 i1 GGUF?

The files are on Hugging Face in the mradermacher/Euryale-1.3-longLORA-70b-rope8-32k-fp16-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 Euryale 1.3 longLORA 70b rope8 32k fp16 i1 use?

Hugging Face lists the license as llama2. 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; it requires about 17.7 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model has no vision capability.

What license applies to this model?

The model is released under the llama2 license.

Other GGUFs of Euryale-1.3-longLORA-70b-rope8-32k-fp16

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Euryale models

All Euryale →

Other large models

All large models →