XL

xLAM 8x22b R

XlamGGUF by RichardErkhovUpdated 2024-11-05
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant46.2 GB
Quick answer

xLAM 8x22b R needs about 82.9 GB of memory at IQ4_NL (a 80.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 18 quants, from 46.2 GB (Q5_0) to 149.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

xLAM 8x22b R is a 141B-parameter Xlam model in GGUF format, quantized by RichardErkhov. Its trained context length is 64K tokens. The repository has 18 quant files, from 46.2 GB (Q5_0) to 149.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_046.2 GB (2 parts) 48.6 GB
Too big Get file →
Q2_K52.1 GB (2 parts) 54.5 GB
Too big Get file →
Q3_K_S61.5 GB (2 parts) 63.9 GB
Too big Get file →
Q3_K67.8 GB (2 parts) 70.2 GB
Too big Get file →
Q3_K_M67.8 GB (2 parts) 70.2 GB
Too big Get file →
Q3_K_L72.6 GB (2 parts) 75.0 GB
Too big Get file →
IQ4_XS76.4 GB (2 parts) 78.7 GB
Too big Get file →
Q4_079.5 GB (2 parts) 81.9 GB
Too big Get file →
IQ4_NL80.5 GB (3 parts) 82.9 GB
Too big Get file →
Q4_K_S80.5 GB (3 parts) 82.9 GB
Too big Get file →
Q4_K85.6 GB (3 parts) 88.0 GB
Too big Get file →
Q4_188.3 GB (3 parts) 90.6 GB
Too big Get file →
Q5_K_S97.0 GB (3 parts) 99.4 GB
Too big Get file →
Q5_K100.0 GB (3 parts) 102.4 GB
Too big Get file →
Q5_K_M100.0 GB (3 parts) 102.4 GB
Too big Get file →
Q5_1105.7 GB (3 parts) 108.1 GB
Too big Get file →
Q6_K115.5 GB (3 parts) 117.9 GB
Too big Get file →
Q8_0149.4 GB (4 parts) 151.8 GB
Too big Get file →

What GPU do you need for xLAM 8x22b R?

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: no quant fits at an 8K context.

Which xLAM 8x22b R quant should you choose?

IQ4_NL (80.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q5_0 at 46.2 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters141B (approximate, mixture of experts)
Layers56
Trained context65,536 tokens
KV cache (fp16)224 KB per token

Source

Quantized byRichardErkhov
FamilyXlam
Downloads (HF)204
Last updated2024-11-05

Frequently asked questions about xLAM 8x22b R

How much VRAM does xLAM 8x22b R need?

About 82.9 GB at IQ4_NL with an 8K context window. That is the 80.5 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 xLAM 8x22b R on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 48.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of xLAM 8x22b R GGUF?

It depends on the quant: Q5_0 is 46.2 GB, Q2_K is 52.1 GB, Q3_K_S is 61.5 GB, Q3_K is 67.8 GB, Q3_K_M is 67.8 GB, Q3_K_L is 72.6 GB and 12 more.

What context length does xLAM 8x22b R support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download xLAM 8x22b R GGUF?

The files are on Hugging Face in the RichardErkhov/Salesforce_-_xLAM-8x22b-r-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 xLAM 8x22b R use?

Hugging Face lists the license as cc-by-nc-4.0. 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 RichardErkhov

All by RichardErkhov →

More Xlam models

All Xlam →

Other large models

All large models →