RH

Rhea 72b v0.5 i1

RheaGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters72.3B
Context32K
Layers80
Architecturellama
Smallest quant20.4 GB
Quick answer

Rhea 72b v0.5 i1 needs about 69.7 GB of memory at Q4_K_M (a 47.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 19 quants, from 20.4 GB (IQ1_S) to 47.7 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 85.9 GB.

Rhea 72b v0.5 i1 – 72.3B parameter Llama model in GGUF format

Rhea 72b v0.5 i1 is a 72.3B parameter Llama architecture model fine‑tuned with the nox framework. It supports a 32768 token context window and is released under the Apache‑2.0 license.

Good at

  • Large context handling
  • High parameter count for detailed generation
  • Open‑source licensing

Limits

  • No vision support
  • Requires large VRAM for full precision
  • No mixture of experts

Best for

  • Complex text generation
  • Research prototyping
  • Long‑form content creation

Who it’s for. Researchers and developers needing a large Llama model with a 32k token context. The model is suitable for experimentation and deployment in environments with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S20.4 GB 42.3 GB
Too big Get file →
IQ1_M21.7 GB 43.7 GB
Too big Get file →
IQ2_XXS23.9 GB 45.9 GB
Too big Get file →
IQ2_XS25.9 GB 47.9 GB
Too big Get file →
IQ2_S27.5 GB 49.5 GB
Too big Get file →
IQ2_M29.3 GB 51.3 GB
Too big Get file →
Q2_K31.0 GB 53.0 GB
Too big Get file →
IQ3_XXS31.8 GB 53.8 GB
Too big Get file →
IQ3_XS33.9 GB 55.9 GB
Too big Get file →
IQ3_S35.5 GB 57.5 GB
Too big Get file →
Q3_K_S35.5 GB 57.5 GB
Too big Get file →
IQ3_M37.2 GB 59.2 GB
Too big Get file →
Q3_K_M39.2 GB 61.2 GB
Too big Get file →
Q3_K_L42.5 GB 64.4 GB
Too big Get file →
IQ4_XS42.7 GB 64.7 GB
Too big Get file →
IQ4_NL45.0 GB 66.9 GB
Too big Get file →
Q4_045.1 GB 67.1 GB
Too big Get file →
Q4_K_S45.2 GB 67.2 GB
Too big Get file →
Q4_K_M47.7 GB 69.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (20.36 GB file, ~42.3 GB memory at 8k context). For 12 GB VRAM, IQ1_M (21.7 GB file, ~43.7 GB memory). For 24 GB VRAM, Q4_K_M (47.73 GB file, ~69.7 GB memory).

What GPU do you need for Rhea 72b v0.5 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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is IQ2_XS (25.9 GB file, about 47.9 GB in use).

Which Rhea 72b v0.5 i1 quant should you choose?

Q4_K_M is the usual starting point for Rhea 72b v0.5 i1: it balances file size and quality well. Here it is a 47.7 GB file.

If memory is tight, the smallest file is IQ1_S at 20.4 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
Parameters72.3B
Layers80
Trained context32,768 tokens
KV cache (fp16)2560 KB per token

Source

Quantized bymradermacher
FamilyRhea
Licenseapache-2.0
Downloads (HF)888
Last updated2024-05-06

Frequently asked questions about Rhea 72b v0.5 i1

How much VRAM does Rhea 72b v0.5 i1 need?

About 69.7 GB at Q4_K_M with an 8K context window. That is the 47.7 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 Rhea 72b v0.5 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 42.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Rhea 72b v0.5 i1 GGUF?

It depends on the quant: IQ1_S is 20.4 GB, IQ1_M is 21.7 GB, IQ2_XXS is 23.9 GB, IQ2_XS is 25.9 GB, IQ2_S is 27.5 GB, IQ2_M is 29.3 GB and 13 more.

What context length does Rhea 72b v0.5 i1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 21.5 GB at 8K and 85.9 GB at 32K.

Where can I download Rhea 72b v0.5 i1 GGUF?

The files are on Hugging Face in the mradermacher/Rhea-72b-v0.5-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 Rhea 72b v0.5 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 Rhea 72b v0.5 i1 on 8 GB VRAM?

No, the smallest quant requires at least 20.36 GB file size and ~42.3 GB memory at 8k context, exceeding 8 GB VRAM.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Rhea-72b-v0.5

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Rhea models

All Rhea →

Other large models

All large models →