RI

Rizla 69

RizlaGGUF by mradermacherUpdated 2024-11-05
Download on Hugging Face
Parameters68.8B
Context32K
Layers76
Architecturellama
Smallest quant25.8 GB
Quick answer

Rizla 69 needs about 62.6 GB of memory at Q4_K_M (a 41.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 9 quants, from 25.8 GB (Q2_K) to 48.8 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 81.6 GB.

Rizla 69 is a 68.8B-parameter Rizla model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 9 quant files, from 25.8 GB (Q2_K) to 48.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.8 GB 46.7 GB
Too big Get file →
Q3_K_S30.1 GB 51.0 GB
Too big Get file →
Q3_K_M33.6 GB 54.5 GB
Too big Get file →
Q3_K_L36.6 GB 57.5 GB
Too big Get file →
IQ4_XS37.2 GB 58.1 GB
Too big Get file →
Q4_K_S39.3 GB 60.2 GB
Too big Get file →
Q4_K_M41.7 GB 62.6 GB
Too big Get file →
Q5_K_S47.5 GB 68.4 GB
Too big Get file →
Q5_K_M48.8 GB 69.7 GB
Too big Get file →

What GPU do you need for Rizla 69?

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 Q2_K (25.8 GB file, about 46.7 GB in use).

Which Rizla 69 quant should you choose?

Q4_K_M is the usual starting point for Rizla 69: it balances file size and quality well. Here it is a 41.7 GB file.

If memory is tight, the smallest file is Q2_K at 25.8 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
Parameters68.8B
Layers76
Trained context32,768 tokens
KV cache (fp16)2432 KB per token

Source

Quantized bymradermacher
FamilyRizla
Base modelrizla/rizla-69
Licenseapache-2.0
Downloads (HF)19
Last updated2024-11-05

Frequently asked questions about Rizla 69

How much VRAM does Rizla 69 need?

About 62.6 GB at Q4_K_M with an 8K context window. That is the 41.7 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 Rizla 69 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 46.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Rizla 69 GGUF?

It depends on the quant: Q2_K is 25.8 GB, Q3_K_S is 30.1 GB, Q3_K_M is 33.6 GB, Q3_K_L is 36.6 GB, IQ4_XS is 37.2 GB, Q4_K_S is 39.3 GB and 3 more.

What context length does Rizla 69 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 20.4 GB at 8K and 81.6 GB at 32K.

Where can I download Rizla 69 GGUF?

The files are on Hugging Face in the mradermacher/rizla-69-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 Rizla 69 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.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Rizla models

All Rizla →

Other large models

All large models →